Search

Your search keyword '"David Picard"' showing total 42 results
Start Over Author "David Picard" Topic artificial intelligence
42 results on '"David Picard"'

1. SSP-Net: Scalable sequential pyramid networks for real-Time 3D human pose regression

Author

Diogo Carbonera Luvizon, Hedi Tabia, David Picard, MPI Informatics, Informatique, BioInformatique, Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE)-Université Paris-Saclay, Laboratoire d'Informatique Gaspard-Monge (LIGM), and École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel

Subjects
FOS: Computer and information sciences, Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Signal Processing, Computer Science - Computer Vision and Pattern Recognition, Neural nets, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Computer vision, Computer Vision and Pattern Recognition, 3D Human pose estimation, Software, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

In this paper we propose a highly scalable convolutional neural network, end-to-end trainable, for real-time 3D human pose regression from still RGB images. We call this approach the Scalable Sequential Pyramid Networks (SSP-Net) as it is trained with refined supervision at multiple scales in a sequential manner. Our network requires a single training procedure and is capable of producing its best predictions at 120 frames per second (FPS), or acceptable predictions at more than 200 FPS when cut at test time. We show that the proposed regression approach is invariant to the size of feature maps, allowing our method to perform multi-resolution intermediate supervisions and reaching results comparable to the state-of-the-art with very low resolution feature maps. We demonstrate the accuracy and the effectiveness of our method by providing extensive experiments on two of the most important publicly available datasets for 3D pose estimation, Human3.6M and MPI-INF-3DHP. Additionally, we provide relevant insights about our decisions on the network architecture and show its flexibility to meet the best precision-speed compromise., Under review at PR

Published
2023
Full Text
View/download PDF

2. Consensus-Based Optimization for 3D Human Pose Estimation in Camera Coordinates

Author

Diogo C. Luvizon, David Picard, Hedi Tabia, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Laboratoire d'Informatique Gaspard-Monge (LIGM), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, Informatique, BioInformatique, Systèmes Complexes (IBISC), and Université d'Évry-Val-d'Essonne (UEVE)-Université Paris-Saclay

Subjects
FOS: Computer and information sciences, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Human pose estimation, Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Deep learning, Computer Vision and Pattern Recognition, Motion capture, Neural networks, Software, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint. Alternatively, we propose a 3D human pose estimation method in camera coordinates, which allows effective combination of 2D annotated data and 3D poses and a straightforward multi-view generalization. To that end, we cast the problem as a view frustum space pose estimation, where absolute depth prediction and joint relative depth estimations are disentangled. Final 3D predictions are obtained in camera coordinates by the inverse camera projection. Based on this, we also present a consensus-based optimization algorithm for multi-view predictions from uncalibrated images, which requires a single monocular training procedure. Although our method is indirectly tied to the training camera intrinsics, it still converges for cameras with different intrinsic parameters, resulting in coherent estimations up to a scale factor. Our method improves the state of the art on well known 3D human pose datasets, reducing the prediction error by 32% in the most common benchmark. We also reported our results in absolute pose position error, achieving 80~mm for monocular estimations and 51~mm for multi-view, on average., Comment: Source code is available at https://github.com/dluvizon/3d-pose-consensus

Published
2022
Full Text
View/download PDF

3. Deep-Learning Technology for Book Conservation Assessment in Libraries and Archives

Author

Valérie Lee, Lahcen Yamoun, Michel Jordan, Camille Simon Chane, David Picard, Julien Longhi, and lee, valerie

Subjects
book conservation, Artificial intelligence, libraries, [SHS] Humanities and Social Sciences, [INFO] Computer Science [cs], deep-learning, archives
Abstract

One of the primary goals of Libraries and Archives is the conservation of their collections in order to pass them on to future generations. The large number of books kept in storage makes this task particularly challenging. Artificial intelligence offers the possibility of processing large volumes of data in a short period of time, but this technology has not been used for book conservation. A team of artificial intelligence scientists and one conservator is now developing a tool to automatically assess the conservation state of a binding at any given time.

Published
2022

4. Distributed optimization for deep learning with gossip exchange

Author

Michael Blot, Nicolas Thome, David Picard, Matthieu Cord, Machine Learning and Information Access (MLIA), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), and CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)

Subjects
Optimization, 0209 industrial biotechnology, Theoretical computer science, Computer science, Cognitive Neuroscience, Distributed gradient descent, Gossip, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Convolutional neural network, 020901 industrial engineering & automation, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Learning, Artificial neural network, business.industry, Deep learning, Deep, Local variable, Computer Science Applications, Stochastic gradient descent, Asynchronous communication, 020201 artificial intelligence & image processing, Artificial intelligence, business, Neural networks
Abstract

International audience; We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization setup uses several threads, each applying individual gradient descents on a local variable. We propose a new way of sharing information between different threads based on gossip algorithms that show good consensus convergence properties. Our method called GoSGD has the advantage to be fully asynchronous and decentralized.

Published
2019
Full Text
View/download PDF

5. Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving

Author

David Picard, Alexandre Briot, Victor Besnier, and VALEO

Subjects
FOS: Computer and information sciences, Observer (quantum physics), Computer science, media_common.quotation_subject, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Inference, 02 engineering and technology, Machine learning, computer.software_genre, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Uncertainty estimation, 0202 electrical engineering, electronic engineering, information engineering, Segmentation, Function (engineering), ComputingMilieux_MISCELLANEOUS, media_common, Measure (data warehouse), Training set, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Image segmentation, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer
Abstract

In this paper, we show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving, by triggering a fallback behavior if a target accuracy cannot be guaranteed. We introduce a new uncertainty measure based on disagreeing predictions as measured by a dissimilarity function. We propose to estimate this dissimilarity by training a deep neural architecture in parallel to the task-specific network. It allows this observer to be dedicated to the uncertainty estimation, and let the task-specific network make predictions. We propose to use self-supervision to train the observer, which implies that our method does not require additional training data. We show experimentally that our proposed approach is much less computationally intensive at inference time than competing methods (e.g. MCDropout), while delivering better results on safety-oriented evaluation metrics on the CamVid dataset, especially in the case of glare artifacts.

Published
2021
Full Text
View/download PDF

6. DIABLO: Dictionary-based attention block for deep metric learning

Author

Aymeric Histace, Edouard Klein, Pierre Jacob, David Picard, Institut Jean-Nicod (IJN), Département d'Etudes Cognitives - ENS Paris (DEC), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École des hautes études en sciences sociales (EHESS)-Collège de France (CdF (institution))-Centre National de la Recherche Scientifique (CNRS)-Département de Philosophie - ENS Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Laboratoire d'Informatique Gaspard-Monge (LIGM), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Département de Philosophie - ENS Paris, École normale supérieure - Paris (ENS Paris)-École normale supérieure - Paris (ENS Paris)-Centre National de la Recherche Scientifique (CNRS)-École des hautes études en sciences sociales (EHESS)-Département d'Etudes Cognitives - ENS Paris (DEC), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel (UNIV GUSTAVE EIFFEL), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Université de Cergy Pontoise (UCP), Université Paris-Seine-Université Paris-Seine-Centre National de la Recherche Scientifique (CNRS), Machine Learning and Computational Biology (ABC), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, computer.software_genre, 01 natural sciences, Image (mathematics), Discriminative model, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Artificial Intelligence, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 010306 general physics, ComputingMilieux_MISCELLANEOUS, Block (data storage), business.industry, Sampling (statistics), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Signal Processing, Metric (mathematics), Embedding, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, Focus (optics), business, Feature learning, computer, Software, Natural language processing
Abstract

Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks. Recent contributions mostly address the training part (loss functions, sampling strategies, etc.), while a few works focus on improving the discriminative power of the image representation. In this paper, we propose DIABLO, a dictionary-based attention method for image embedding. DIABLO produces richer representations by aggregating only visually-related features together while being easier to train than other attention-based methods in deep metric learning. This is experimentally confirmed on four deep metric learning datasets (Cub-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval) for which DIABLO shows state-of-the-art performances., Pre-print. Accepted for publication at Pattern Recognition Letters

Published
2020
Full Text
View/download PDF

7. Deepzzle: Solving Visual Jigsaw Puzzles with Deep Learning andShortest Path Optimization

Author

David Picard, Hedi Tabia, Marie-Morgane Paumard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Laboratoire d'Informatique Gaspard-Monge (LIGM), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, Informatique, BioInformatique, Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE)-Université Paris-Saclay, Fondation des Sciences du Patrimoine, ANR-17-EURE-0021,PSGS-HCH,Paris Seine Graduate School of Humanities Creation Heritage(2017), and CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Space (commercial competition), GraphImage reassembly, Image (mathematics), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 11. Sustainability, 0202 electrical engineering, electronic engineering, information engineering, business.industry, Deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Erosion (morphology), Computer Graphics and Computer-Aided Design, Graph, Jigsaw puzzle, Metric (mathematics), Shortest path problem, Branch-cutcultural heritage, Graph (abstract data type), 020201 artificial intelligence & image processing, Artificial intelligence, business, Algorithm, Software
Abstract

We tackle the image reassembly problem with wide space between the fragments, in such a way that the patterns and colors continuity is mostly unusable. The spacing emulates the erosion of which the archaeological fragments suffer. We crop-square the fragments borders to compel our algorithm to learn from the content of the fragments. We also complicate the image reassembly by removing fragments and adding pieces from other sources. We use a two-step method to obtain the reassemblies: 1) a neural network predicts the positions of the fragments despite the gaps between them; 2) a graph that leads to the best reassemblies is made from these predictions. In this paper, we notably investigate the effect of branch-cut in the graph of reassemblies. We also provide a comparison with the literature, solve complex images reassemblies, explore at length the dataset, and propose a new metric that suits its specificities. Keywords: image reassembly, jigsaw puzzle, deep learning, graph, branch-cut, cultural heritage

Published
2020
Full Text
View/download PDF

8. Human pose regression by combining indirect part detection and contextual information

Author

Hedi Tabia, Diogo C. Luvizon, David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Advanced Technologies, Samsung Research Institute, Samsung, Informatique, BioInformatique, Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE), Laboratoire d'Informatique Gaspard-Monge (LIGM), Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM), and Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, Source code, Interface (Java), Computer science, media_common.quotation_subject, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Neural nets, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Machine learning, computer.software_genre, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Function (engineering), Pose, media_common, Ground truth, Artificial neural network, business.industry, Human pose estimation, General Engineering, 020207 software engineering, Computer Graphics and Computer-Aided Design, Human-Computer Interaction, Automatic image annotation, Feature (computer vision), 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, computer
Abstract

International audience; In this paper, we tackle the problem of human pose estimation from still images, which is a very active topic, specially due to its several applications, from image annotation to human-machine interface. We use the soft-argmax function to convert feature maps directly to body joint coordinates, resulting in a fully differentiable framework. Our method is able to learn heat maps representations indirectly, without additional steps of artificial ground truth generation. Consequently, contextual information can be included to the pose predictions in a seamless way. We evaluated our method on two challenging datasets, the Leeds Sports Poses (LSP) and the MPII Human Pose datasets, reaching the best performance among all the existing regression methods. Source code available at: https://github.com/dluvizon/pose-regression.

Published
2019
Full Text
View/download PDF

9. Metric Learning with HORDE: High-Order Regularizer for Deep Embeddings

Author

Pierre Jacob, Aymeric Histace, David Picard, Edouard Klein, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), École des Ponts ParisTech (ENPC), Pôle judiciaire de la gendarmerie nationale (PJGN), ALICE project, and Histace, Aymeric

Subjects
FOS: Computer and information sciences, Computer science, business.industry, Computer Vision and Pattern Recognition (cs.CV), Feature vector, Computer Science - Computer Vision and Pattern Recognition, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 02 engineering and technology, 010501 environmental sciences, Similarity measure, 01 natural sciences, Regularization (mathematics), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Discriminative model, Outlier, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, High order, business, 0105 earth and related environmental sciences
Abstract

Learning an effective similarity measure between image representations is key to the success of recent advances in visual search tasks (e.g. verification or zero-shot learning). Although the metric learning part is well addressed, this metric is usually computed over the average of the extracted deep features. This representation is then trained to be discriminative. However, these deep features tend to be scattered across the feature space. Consequently, the representations are not robust to outliers, object occlusions, background variations, etc. In this paper, we tackle this scattering problem with a distribution-aware regularization named HORDE. This regularizer enforces visually-close images to have deep features with the same distribution which are well localized in the feature space. We provide a theoretical analysis supporting this regularization effect. We also show the effectiveness of our approach by obtaining state-of-the-art results on 4 well-known datasets (Cub-200-2011, Cars-196, Stanford Online Products and Inshop Clothes Retrieval)., Camera-ready for our ICCV 2019 paper (poster)

Published
2019

10. Efficient Codebook and Factorization for Second Order Representation Learning

Author

Aymeric Histace, David Picard, Pierre Jacob, Edouard Klein, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), PJGN\IRCGN, ALICE Project, and Histace, Aymeric

Subjects
FOS: Computer and information sciences, Theoretical computer science, Computer science, Computer Vision and Pattern Recognition (cs.CV), Feature extraction, Computer Science - Computer Vision and Pattern Recognition, metric learning, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, image retrieval, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Factorization, 0202 electrical engineering, electronic engineering, information engineering, Image retrieval, 0105 earth and related environmental sciences, business.industry, Deep learning, Cognitive neuroscience of visual object recognition, Codebook, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], codebook strategy, second-order representation, Manifold, Compact space, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business, Feature learning
Abstract

Learning rich and compact representations is an open topic in many fields such as object recognition or image retrieval. Deep neural networks have made a major breakthrough during the last few years for these tasks but their representations are not necessary as rich as needed nor as compact as expected. To build richer representations, high order statistics have been exploited and have shown excellent performances, but they produce higher dimensional features. While this drawback has been partially addressed with factorization schemes, the original compactness of first order models has never been retrieved, or at the cost of a strong performance decrease. Our method, by jointly integrating codebook strategy to factorization scheme, is able to produce compact representations while keeping the second order performances with few additional parameters. This formulation leads to state-of-the-art results on three image retrieval datasets., Comment: Accepted at IEEE International Conference on Image Processing (ICIP) 2019

Published
2019

11. 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning

Author

Hedi Tabia, Diogo C. Luvizon, David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), Multimedia Indexation and Data Integration (MIDI), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), and Luvizon, Diogo

Subjects
FOS: Computer and information sciences, Computer science, business.industry, Computer Vision and Pattern Recognition (cs.CV), Deep learning, Computer Science - Computer Vision and Pattern Recognition, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, 02 engineering and technology, 3D pose estimation, Machine learning, computer.software_genre, Visualization, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Action (philosophy), 0202 electrical engineering, electronic engineering, information engineering, Task analysis, Action recognition, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Pose
Abstract

Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we propose a multitask framework for jointly 2D and 3D pose estimation from still images and human action recognition from video sequences. We show that a single architecture can be used to solve the two problems in an efficient way and still achieves state-of-the-art results. Additionally, we demonstrate that optimization from end-to-end leads to significantly higher accuracy than separated learning. The proposed architecture can be trained with data from different categories simultaneously in a seamlessly way. The reported results on four datasets (MPII, Human3.6M, Penn Action and NTU) demonstrate the effectiveness of our method on the targeted tasks., To appear in CVPR 2018

Published
2018

12. Asynchronous gossip principal components analysis

Author

David Picard, Philippe-Henri Gosselin, Jérôme Fellus, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), and CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)

Subjects
Theoretical computer science, Computer science, Cognitive Neuroscience, Distributed computing, Distributed Machine Learning, 020206 networking & telecommunications, 02 engineering and technology, Dimensionality reduction, Computer Science Applications, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Artificial Intelligence, Gossip, Asynchronous communication, Principal component analysis, 0202 electrical engineering, electronic engineering, information engineering, Gossip protocols, 020201 artificial intelligence & image processing, Gossip protocol, Protocol (object-oriented programming), Equivalence (measure theory)
Abstract

International audience; This paper deals with Principal Components Analysis (PCA) of data spread over a network where central coordination and synchronous communication between networking nodes are forbidden. We propose an asynchronous and decentralized PCA algorithm dedicated to large scale problems, where " large " simultaneously applies to dimensionality, number of observations and network size. It is based on the integration of a dimension reduction step into a Gossip consensus protocol. Unlike other approaches, a straightforward dual formulation makes it suitable when observed dimensions are distributed. We theoretically show its equivalence with a centralized PCA under a low-rank assumption on training data. An experimental analysis reveals that it achieves a good accuracy with a reasonable communication cost even when the low-rank assumption is relaxed.

Published
2015
Full Text
View/download PDF

13. Leveraging Implicit Spatial Information In Global Features For Image Retrieval

Author

Edouard Klein, Aymeric Histace, Pierre Jacob, David Picard, Histace, Aymeric, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), Multimedia Indexation and Data Integration (MIDI), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), Machine Learning and Information Access (MLIA), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), ASTRE [Cergy-Pontoise], Pôle judiciaire de la gendarmerie nationale (PJGN), and ALICE Project

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0211 other engineering and technologies, 02 engineering and technology, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Tensor (intrinsic definition), 0202 electrical engineering, electronic engineering, information engineering, Representation (mathematics), Spatial analysis, Image retrieval, 021110 strategic, defence & security studies, business.industry, Dimensionality reduction, Aggregate (data warehouse), Process (computing), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Visualization, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

Most image retrieval methods use global features that aggregate local distinctive patterns into a single representation. However, the aggregation process destroys the relative spatial information by considering orderless sets of local descriptors. We propose to integrate relative spatial information into the aggregation process by taking into account co-occurrences of local patterns in a tensor framework. The resulting signature called Improved Spatial Tensor Aggregation (ISTA) is able to reach state of the art performances on well known datasets such as Holidays, Oxford5k and Paris6k., Comment: 8 pages, 2 figures and 1 table. Draft paper for conference, IEEE International Conference on Image Processing (ICIP) 2018

Published
2018

14. Image Reassembly Combining Deep Learning and Shortest Path Problem

Author

Marie-Morgane Paumard, David Picard, Hedi Tabia, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), and Paumard, Marie-Morgane

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, Image (mathematics), Set (abstract data type), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Position (vector), Fragments reassembly, 0202 electrical engineering, electronic engineering, information engineering, 0105 earth and related environmental sciences, business.industry, Deep learning, ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS, deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], cultural heritage, jigsaw puzzle, Shortest path problem, 020201 artificial intelligence & image processing, Artificial intelligence, State (computer science), business, Algorithm, image classification
Abstract

This paper addresses the problem of reassembling images from disjointed fragments. More specifically, given an unordered set of fragments, we aim at reassembling one or several possibly incomplete images. The main contributions of this work are: 1) several deep neural architectures to predict the relative position of image fragments that outperform the previous state of the art; 2) casting the reassembly problem into the shortest path in a graph problem for which we provide several construction algorithms depending on available information; 3) a new dataset of images taken from the Metropolitan Museum of Art (MET) dedicated to image reassembly for which we provide a clear setup and a strong baseline., ECCV 2018

Published
2018
Full Text
View/download PDF

15. Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings

Author

Matthieu Cord, David Picard, Remi Cadene, Laure Soulier, Nicolas Thome, and Micael Carvalho

Subjects
Scheme (programming language), FOS: Computer and information sciences, Information retrieval, Computer Science - Computation and Language, Computer science, business.industry, Deep learning, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Space (commercial competition), Popularity, Image (mathematics), Computer Science - Information Retrieval, Modal, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, Representation (mathematics), business, computer, Computation and Language (cs.CL), Information Retrieval (cs.IR), computer.programming_language
Abstract

Designing powerful tools that support cooking activities has rapidly gained popularity due to the massive amounts of available data, as well as recent advances in machine learning that are capable of analyzing them. In this paper, we propose a cross-modal retrieval model aligning visual and textual data (like pictures of dishes and their recipes) in a shared representation space. We describe an effective learning scheme, capable of tackling large-scale problems, and validate it on the Recipe1M dataset containing nearly 1 million picture-recipe pairs. We show the effectiveness of our approach regarding previous state-of-the-art models and present qualitative results over computational cooking use cases., Comment: accepted at the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, 2018

Published
2018
Full Text
View/download PDF

16. Jigsaw Puzzle Solving Using Local Feature Co-occurrences In Deep Neural Networks

Author

Marie-Morgane Paumard, Hedi Tabia, David Picard, Paumard, Marie-Morgane, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), Multimedia Indexation and Data Integration (MIDI), and CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Relation (database), Computer science, Image classification, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Machine Learning (stat.ML), 02 engineering and technology, Iterative reconstruction, Machine Learning (cs.LG), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Statistics - Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, Fragment reassembly, Greedy algorithm, business.industry, Deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Jigsaw, Jigsaw puzzle, Feature (computer vision), Cultural heritage, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

Archaeologists are in dire need of automated object reconstruction methods. Fragments reassembly is close to puzzle problems, which may be solved by computer vision algorithms. As they are often beaten on most image related tasks by deep learning algorithms, we study a classification method that can solve jigsaw puzzles. In this paper, we focus on classifying the relative position: given a couple of fragments, we compute their local relation (e.g. on top). We propose several enhancements over the state of the art in this domain, which is outperformed by our method by 25\%. We propose an original dataset composed of pictures from the Metropolitan Museum of Art. We propose a greedy reconstruction method based on the predicted relative positions., Comment: ICIP 2018

Published
2018

17. Learning features combination for human action recognition from skeleton sequences

Author

Diogo C. Luvizon, Hedi Tabia, David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), and Brazilian National Council for Scientific and Technological Development (CNPq)

Subjects
Feature vector, 02 engineering and technology, Learning Algorithm, Machine learning, computer.software_genre, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Human action recognition, Mathematics, Feature combination, business.industry, Nonparametric statistics, 020207 software engineering, Pattern recognition, Discriminant, Signal Processing, Action recognition, Learning methods, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, computer, Classifier (UML), Software, Large margin nearest neighbor
Abstract

International audience; Human action recognition is a challenging task due to the complexity of human movements and to the variety among the same actions performed by distinct subjects. Recent technologies provide the skeletal representation of human body extracted in real time from depth maps, which is a high dis-criminant information for efficient action recognition. In this context, we present a new framework for human action recognition from skeleton sequences. We propose extracting sets of spatial and temporal local features from subgroups of joints, which are aggregated by a robust method based on the VLAD algorithm and a pool of clusters. Several feature vectors are then combined by a metric learning method inspired by the LMNN algorithm with the objective to improve the classification accuracy using the nonparametric k-NN classifier. We evaluated our method on three public datasets, including the MSR-Action3D, the UTKinect-Action3D, and the Florence 3D Actions dataset. As a result, the proposed framework performance overcomes the methods in the state of the art on all the experiments.

Published
2017
Full Text
View/download PDF

18. Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

Author

Diogo C. Luvizon, Hedi Tabia, David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), IMAGINE [Marne-la-Vallée], Laboratoire d'Informatique Gaspard-Monge (LIGM), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel-École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, Informatique, BioInformatique, Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE)-Université Paris-Saclay, Brazilian National Council for Scientific and Technological Development, and CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Machine learning, computer.software_genre, Deep Learning, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Humans, Human action recognition, Pose, Artificial neural network, Human pose estimation, business.industry, Applied Mathematics, Deep learning, Visualization, Task (computing), Computational Theory and Mathematics, Task analysis, RGB color model, 020201 artificial intelligence & image processing, Multitask deep learning, Computer Vision and Pattern Recognition, Artificial intelligence, business, computer, Algorithms, Neural networks, Software
Abstract

Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately. In this work, we propose a multi-task framework for jointly estimating 2D or 3D human poses from monocular color images and classifying human actions from video sequences. We show that a single architecture can be used to solve both problems in an efficient way and still achieves state-of-the-art or comparable results at each task while running at more than 100 frames per second. The proposed method benefits from high parameters sharing between the two tasks by unifying still images and video clips processing in a single pipeline, allowing the model to be trained with data from different categories simultaneously and in a seamlessly way. Additionally, we provide important insights for end-to-end training the proposed multi-task model by decoupling key prediction parts, which consistently leads to better accuracy on both tasks. The reported results on four datasets (MPII, Human3.6M, Penn Action and NTU RGB+D) demonstrate the effectiveness of our method on the targeted tasks. Our source code and trained weights are publicly available at https://github.com/dluvizon/deephar., Comment: Accepted to TPAMI. arXiv admin note: text overlap with arXiv:1802.09232

Published
2020
Full Text
View/download PDF

19. Efficient image signatures and similarities using tensor products of local descriptors

Author

David Picard, Philippe-Henri Gosselin, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), and Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)

Subjects
Contextual image classification, business.industry, Feature vector, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, Pattern recognition, 02 engineering and technology, ComputingMethodologies_PATTERNRECOGNITION, Automatic image annotation, Tensor product, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Kernel (image processing), Image texture, Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Visual Word, Artificial intelligence, business, Image retrieval, Software, Mathematics
Abstract

HighlightsÂ? New features for image search and object categorization. Â? Linearization of Kernels on Bags. Â? Derivative of second order statistics. Â? Linear/dot product metric. In this paper, we introduce a novel image signature effective in both image retrieval and image classification. Our approach is based on the aggregation of tensor products of discriminant local features, named VLATs (vector of locally aggregated tensors). We also introduce techniques for the packing and the fast comparison of VLATs. We present connections between VLAT and methods like kernel on bags and Fisher vectors. Finally, we show the ability of our method to be effective for two different retrieval problems, thanks to experiments carried out on similarity search and classification datasets.

Published
2013
Full Text
View/download PDF

20. Non-negative dictionary learning for paper watermark similarity

Author

Georg Dietz, David Picard, Thomas Henn, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), papierstruktur.de, and Picard, David

Subjects
[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, business.industry, Computer science, Data_MISCELLANEOUS, ComputingMilieux_LEGALASPECTSOFCOMPUTING, 020207 software engineering, Watermark, 02 engineering and technology, Visualization, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Similarity (network science), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, Dictionary learning, Digital watermarking
Abstract

International audience; In this paper, we investigate the retrieval of paper watermark by visual similarity. We propose to perform the visual similarity by encoding small regions of the watermark using a non-negative dictionary optimized on a large collection of watermarks. The local codes are then aggregated into a single vector representing the whole watermark. Experiments are carried out on a test of tracings (manual binarization of watermarks).

Published
2016
Full Text
View/download PDF

21. Preserving local spatial information in image similarity using tensor aggregation of local features

Author

David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), and Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)

Subjects
Similarity (geometry), Matching (graph theory), Layout, Object detection, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-invariant feature transform, 02 engineering and technology, Tensor (intrinsic definition), Computer Science::Multimedia, 0202 electrical engineering, electronic engineering, information engineering, Spatial analysis, Image retrieval, Mathematics, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, Computer Science::Computer Vision and Pattern Recognition, 020201 artificial intelligence & image processing, Artificial intelligence, Image databases, business, Image representation
Abstract

International audience; In this paper, we propose an aggregation scheme of local descriptors that preserves local spatial information. Our method is based on the binary product of similarities of nearby matching pairs of descriptors. The similarities are linearized using a tensor framework. We show our approach can be used with any local descriptors, handcrafted like SIFT, or learned like the outputs of convolutional layers in deep neural networks. We perform experiments on the Holidays dataset that show the soundness of the approach.

Published
2016
Full Text
View/download PDF

22. Image Retrieval Over Networks: Active Learning Using Ant Algorithm

Author

David Picard, Matthieu Cord, Arnaud Revel, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Laboratoire Informatique, Image et Interaction - EA 2118 (L3I), Université de La Rochelle (ULR), and La Rochelle Université (ULR)

Subjects
Information retrieval, Matching (graph theory), Computer science, Active learning (machine learning), business.industry, Relevance feedback, 02 engineering and technology, Similarity measure, Machine learning, computer.software_genre, Content-based image retrieval, TRECVID, Computer Science Applications, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 020204 information systems, Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, 020201 artificial intelligence & image processing, Mobile agent, Artificial intelligence, Electrical and Electronic Engineering, business, computer, Image retrieval
Abstract

International audience; In this article, we present a framework for distributed content based image retrieval with online learning based on ant-like mobile agents. Mobile agents crawl the network to find images matching a given example query. The images retrieved are shown to the user who labels them, following the classical relevant feedback scheme. The labels are used both to improve the similarity measure used for the retrieval and to learn paths leading to sites containing relevant images. The relevant paths are learned in an ethologically inspired way. We made experiments on the trecvid 2005 keyframe dataset showing that learning both the similarity function and the localization of the relevant images leads to a significant improvement. We also present an extension with the reuse of learned paths for later sessions leading to a further improvement.

Published
2008
Full Text
View/download PDF

23. On the Joint Modeling of the Behavior of Social Insects and Their Interaction with Environment by Taking into Account Physical Phenomena Like Anisotropic Diffusion

Author

Benoit Gaudou, Nicolas Cazin, David Picard, Aymeric Histace, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia Indexation and Data Integration (MIDI), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), ASTRE [Cergy-Pontoise], Systèmes Multi-Agents Coopératifs (IRIT-SMAC), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, PEPS Rupture 2011-2012, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Université de Cergy-Pontoise (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), and Histace, Aymeric

Subjects
0106 biological sciences, Bark beetle, Pest Insect, Non-Linear Diffusion, Process (engineering), Computer science, Population, Multi Agent Systems, Système multi-agents, [INFO] Computer Science [cs], 010603 evolutionary biology, 01 natural sciences, Traitement des images, Bark (sound), Forest ecology, GAMA platform, Traitement du signal et de l'image, [INFO]Computer Science [cs], education, H- INFORMATIQUE, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, education.field_of_study, biology, business.industry, 010604 marine biology & hydrobiology, Multi-agent system, Environmental resource management, 15. Life on land, Behavior Modeling, biology.organism_classification, Constraint (information theory), Tree (data structure), [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], GAMMA platform, Artificial intelligence, [INFO.INFO-MA] Computer Science [cs]/Multiagent Systems [cs.MA], business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; This work takes place in the framework of GEODIFF project (funded by CNRS) and deals with the general issue of the social behavior modeling of pest insects with a particular focus on Bark Beetles. Bark Beetles are responsible for pine trees devastation in North America since 2005. In order to stem the problem and to apply an adapted strategy, one should be able to predict the evolution of the population of Bark Beetles. More precisely, a model taking into account a given population of insects (a colony) interacting with its environment, the forest ecosystem, would be very helpful. In a previous work, we aimed to model diffusive phenomenons across the environment using a simple reactive Multi-agent System. Bark beetle use pheromones as a support for recruitment of other bark beetles in the neighborhood in order to achieve a mass attack over a tree. They are first attracted by the ethanol or other phytopheromones emitted by a sick, stressed or dead tree and reinforce the presence of other individuals amongst the targeted tree. Both ethanol and semiochemicals are transported through the forest thanks to the wind, thermic effects and this advection phenomenon is modulated by the topology of the environment, tree and other obstacles distribution. In other words, the environment is involved in the process of a bark beetle attack. The first modeling we used to tackle our objective was not spatially explicit as long as free space propagation only was taken into account (isotropic phenomenon) with no constraint imposed by the environment such as wind. This article is intended to take into account such physical phenomenons and push the modeling one step further by providing predictions driven by measures provided by a Geographical Information System.

Published
2015
Full Text
View/download PDF

24. A Unified framework for local visual descriptors evaluation

Author

Olivier Kihl, David Picard, Philippe-Henri Gosselin, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique

Subjects
Vision and Scene Understanding, Computer science, business.industry, Visual descriptors, Cognitive neuroscience of visual object recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, Pattern recognition, 02 engineering and technology, Object recognition, Video analysis, Image/video retrieval retrieval, Image Processing and Computer Vision, Feature representation, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Artificial Intelligence, Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software
Abstract

Local descriptors are the ground layer of recognition feature based systems for still images and video. We propose a new framework for the design of local descriptors and their evaluation. This framework is based on the descriptors decomposition in three levels: primitive extraction, primitive coding and code aggregation. With this framework, we are able to explain most of the popular descriptors in the literature such as HOG, HOF or SURF. This framework provides an efficient and rigorous approach for the evaluation of local descriptors, and allows us to uncover the best parameters for each descriptor family. Moreover, we are able to extend usual descriptors by changing the code aggregation or adding new primitive coding method. The experiments are carried out on images (VOC 2007) and videos datasets (KTH, Hollywood2, UCF11 and UCF101), and achieve equal or better performances than the literature. Author-HighlightsWe propose a new framework to design local visual descriptors.Descriptors are decomposed in primitive extraction, coding and aggregation.Our framework can explain the most popular descriptors such as HOG, HOF, SURF.The framework allows us a rigorous exploration of the possible combinations of primitives, coding and aggregation.New descriptors are easily obtained by changing one of the steps of our framework.

Published
2015
Full Text
View/download PDF

25. Special Section Guest Editorial: Image Processing for Cultural Heritage

Author

Robert G. Erdmann, Aladine Chetouani, David Picard, and Filippo Stanco

Subjects
Multimedia, business.industry, Computer science, Photography, Image processing, 3D modeling, computer.software_genre, Convolutional neural network, Atomic and Molecular Physics, and Optics, Computer Science Applications, Data modeling, Cultural heritage, Photogrammetry, Special section, Computer vision, Artificial intelligence, Electrical and Electronic Engineering, business, computer
Published
2017
Full Text
View/download PDF

26. PHOTOGRAPHIC PAPER TEXTURE CLASSIFICATION USING MODEL DEVIATION OF LOCAL VISUAL DESCRIPTORS

Author

David Picard, Inbar Fijalkow, Ngoc-Son Vu, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), ICI, and Picard, David

Subjects
Texture compression, Contextual image classification, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, business.industry, Image classification, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, Texture (geology), Image texture analysis, ComputingMethodologies_PATTERNRECOGNITION, Categorization, Image texture, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Texture filtering, Computer vision, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, ComputingMethodologies_COMPUTERGRAPHICS, Feature detection (computer vision), Photographic paper, Mathematics
Abstract

International audience; This paper investigates the classification of photographic paper tex-tures using visual descriptors. Such classification is called fine grain due to the very low inter-class variability. We propose a novel image representation for photographic paper texture categorization, relying on the incorporation of a powerful local descriptor into an efficient higher-order model deviation where texture is represented by com-puting statistics on the occurrences of specific local visual patterns. We perform an evaluation on two different challenging datasets of photographic paper textures and show such advanced methods in-deed outperforms existing descriptors.

Published
2014

27. Incremental learning of latent structural SVM for weakly supervised image classification

Author

Nicolas Thome, Matthieu Cord, Thibaut Durand, David Picard, Machine Learning and Information Access (MLIA), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), and Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)

Subjects
Latent SVM, Computer science, Inference, 02 engineering and technology, Latent variable, 010501 environmental sciences, Machine learning, computer.software_genre, 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Object/Region Detectors, Sliding window protocol, 0202 electrical engineering, electronic engineering, information engineering, Weak Supervision, 0105 earth and related environmental sciences, Contextual image classification, Probabilistic latent semantic analysis, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Image Categorization, Object detection, Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Incremental learning, 020201 artificial intelligence & image processing, Artificial intelligence, business, Visual learning, computer, Subspace topology
Abstract

International audience; Visual learning with weak supervision is a promising re-search area, since it offers the possibility to build large image datasets at reasonable cost. In this paper, we address the prob-lem of weakly supervised object detection, where the goal is to predict the label of the image using object position as latent variable. We propose a new method that builds upon the La-tent Structural SVM (LSSVM) formalism. Specifically, we introduce an original coarse-to-fine approach that limits the evolution of the latent parameter subspace. This incremental strategy drives the learning towards better solutions, provid-ing a model with increased predictive accuracy. In addition, this leads to a significant speed up during learning and infer-ence compared to standard sliding window methods. Experi-ments carried out on Mammal dataset validate the good per-formances and fast training of the method compared to state-of-the-art works.

Published
2014
Full Text
View/download PDF

28. Semantic pooling for image categorization using multiple kernel learning

Author

Matthieu Cord, Thibaut Durand, Nicolas Thome, David Picard, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Machine Learning and Information Access (MLIA), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), and Durand, Thibaut

Subjects
Multiple kernel learning, Contextual image classification, Object detection, business.industry, Computer science, Pooling, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Statistical learning, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Categorization, Index Terms— Image classification, Bag-of-words model in computer vision, Bag-of-words model, Artificial intelligence, business, Image representation, Feature detection (computer vision)
Abstract

International audience; In this paper, we propose a new method for taking into ac-count the spatial information in image categorization. More specifically, we remove the loss of spatial information in Bag of Words related methods by computing the image signature over specific regions selected by object detectors. We propose to select the detectors using Multiple Kernel Learning tech-niques. We carry out experiments on the well known VOC 2007 dataset, and show our semantic pooling obtains promis-ing results.

Published
2014
Full Text
View/download PDF

29. Efficient Metric Learning Based Dimension Reduction Using Sparse Projectors for Image Near Duplicate Retrieval

Author

Philippe-Henri Gosselin, Romain Negrel, and David Picard

Subjects
Linear programming, business.industry, Dimensionality reduction, Pattern recognition, Projection (linear algebra), Automatic image annotation, Metric (mathematics), Memory footprint, Computer vision, Artificial intelligence, business, Image retrieval, Mathematics, Sparse matrix
Abstract

In this paper, we tackle the storage and computational cost of linear projections used in dimensionality reduction for near duplicate image retrieval. We propose a new method based on metric learning with a lower training cost than existing methods. Moreover, by adding a sparsity constraint, we obtain a projection matrix with a low storage and projection cost. We carry out experiments on a well known near duplicate image dataset and show our algorithm behaves correctly. Retrieval performances are shown to be promising when compared to the memory footprint and the projection cost of the obtained sparse matrix.

Published
2014
Full Text
View/download PDF

30. Covariance Descriptors for 3D Shape Matching and Retrieval

Author

Hedi Tabia, Philippe-Henri Gosselin, David Picard, Hamid Laga, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Australian Centre of Plant Functional Genonomics (ACPFG), Grains Research & Devlopement Corporation-Government of South Australia-Australian Government-Australian Research Council [Canberra] (ARC), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Gosselin, Philippe-Henri, 2014 IEEE Conference on Computer Vision and Pattern Recognition Columbus, OH 23-28 June 2014, Tabia, Hedi, Laga, Hamid, and Picard, David

Subjects
Riemannian distance, Geodesic, Covariance matrices, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 02 engineering and technology, Riemannian manifold, Covariance, Topology, Manifold, ComputingMethodologies_PATTERNRECOGNITION, Matérn covariance function, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 3D shape retrieval, 0202 electrical engineering, electronic engineering, information engineering, Rational quadratic covariance function, 020201 artificial intelligence & image processing, Artificial intelligence, Cluster analysis, business, Mathematics, Shape analysis (digital geometry)
Abstract

International audience; Several descriptors have been proposed in the past for 3D shape analysis, yet none of them achieves best perfor- mance on all shape classes. In this paper we propose a novel method for 3D shape analysis using the covariance matrices of the descriptors rather than the descriptors them- selves. Covariance matrices enable efficient fusion of dif- ferent types of features and modalities. They capture, using the same representation, not only the geometric and the spa- tial properties of a shape region but also the correlation of these properties within the region. Covariance matrices, however, lie on the manifold of Symmetric Positive Defi- nite (SPD) tensors, a special type of Riemannian manifolds, which makes comparison and clustering of such matrices challenging. In this paper we study covariance matrices in their native space and make use of geodesic distances on the manifold as a dissimilarity measure. We demonstrate the performance of this metric on 3D face matching and recognition tasks. We then generalize the Bag of Features paradigm, originally designed in Euclidean spaces, to the Riemannian manifold of SPD matrices. We propose a new clustering procedure that takes into account the geometry of the Riemannian manifold. We evaluate the performance of the proposed Bag of Covariance Matrices framework on 3D shape matching and retrieval applications and demonstrate its superiority compared to descriptor-based techniques.

Published
2014

31. Evaluation of Second-order Visual Features for Land-Use Classification

Author

David Picard, Philippe-Henri Gosselin, Romain Negrel, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and Gosselin, Philippe-Henri

Subjects
[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Land use, Computer science, business.industry, Normalization (image processing), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Fisher vector, Data mining, Artificial intelligence, computer.software_genre, business, computer
Abstract

International audience; This paper investigates the use of recent visual features based on second-order statistics, as well as new pro- cessing techniques to improve the quality of features. More specifically, we present and evaluate Fisher Vectors (FV), Vec- tors of Locally Aggregated Descriptors (VLAD), and Vectors of Locally Aggregated Tensors (VLAT). These techniques are combined with several normalization techniques, such as power law normalization and orthogonalisation/whitening of descriptor spaces. Results on the UC Merced land use dataset shows the relevance of these new methods for land-use classification, as well as a significant improvement over Bag-of-Words.

Published
2014

32. Local polynomial space–time descriptors for action classification

Author

Olivier Kihl, Philippe-Henri Gosselin, David Picard, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Projet investissement d'avenir Terrarush, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique

Subjects
business.industry, Search engine indexing, Optical flow, 020207 software engineering, Pattern recognition, 02 engineering and technology, Bivariate analysis, Computer Science Applications, Polynomial basis, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Hardware and Architecture, Orthogonal polynomials, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Vector field, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software, PSPACE, Mathematics, Coding (social sciences)
Abstract

International audience; In this paper we propose to tackle human actions indexing by introducing a new local motion de-scriptor based on a model of the optical flow. We pro-pose to apply a coding step to vector field before the modeling. We use two modeling, a spatial model and a temporal model. The spatial model is computed by pro-jection of optical flow onto bivariate orthogonal poly-nomials. Then, the time evolution of spatial coefficients is modeled with a one dimension polynomial basis. To perform the action classification, we extend recent still image signatures using local descriptors to our proposal and combine them with linear SVM classifiers. The ex-periments are carried out on the well known UCF11 dataset and on the more challenging Hollywood2 ac-tion classification dataset and show promising results.

Published
2014
Full Text
View/download PDF

33. DIMENSIONALITY REDUCTION OF VISUAL FEATURES USING SPARSE PROJECTORS FOR CONTENT-BASED IMAGE RETRIEVAL

Author

Philippe-Henri Gosselin, David Picard, Romain Negrel, Negrel, Romain, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique

Subjects
Computer science, business.industry, Dimensionality reduction, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Indexes, Sparse approximation, Content-based image retrieval, Projection (linear algebra), Automatic image annotation, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Image texture, Sparse matrices, Index Terms— Image retrieval, Visual Word, Artificial intelligence, Image databases, business, Image retrieval, Subspace topology, Sparse matrix, Curse of dimensionality
Abstract

International audience; In web-scale image retrieval, the most effective strategy is to ag-gregate local descriptors into a high dimensionality signature and then reduce it to a small dimensionality. Thanks to this strategy, web-scale image databases can be represented with small index and explored using fast visual similarities. However, the computation of this index has a very high complexity, because of the high di-mensionality of signature projectors. In this work, we propose a new efficient method to greatly reduce the signature dimensionality with low computational and storage costs. Our method is based on the linear projection of the signature onto a small subspace using a sparse projection matrix. We report several experimental results on two standard datasets (Inria Holidays and Oxford) and with 100k image distractors. We show that our method reduces both the projec-tors storage cost and the computational cost of projection step while incurring a very slight loss in mAP (mean Average Precision) per-formance of these computed signatures.

Published
2014

34. 3D shape similarity using vectors of locally aggregated tensors

Author

Hedi Tabia, Hamid Laga, Philippe-Henri Gosselin, David Picard, Gosselin, Philippe-Henri, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia Indexation and Data Integration (MIDI), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Australian Centre of Plant Functional Genonomics (ACPFG), Grains Research & Devlopement Corporation-Government of South Australia-Australian Government-Australian Research Council [Canberra] (ARC), Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Tabia, Hedi, Picard, David, Laga, Hamid, 2013 IEEE International Conference on Image Processing Melbourne, Australia 15-18 September 2013, Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique

Subjects
business.industry, Feature extraction, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 3d model, Dot product, 02 engineering and technology, bag of features, depth images, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Tensor product, Discriminative model, 3D shape retrieval, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, Invariant (mathematics), business, Pose, Image retrieval, Mathematics
Abstract

IEEE International Conference on Image Processing 2013; International audience; In this paper, we present an efficient 3D object retrieval method invariant to scale, orientation and pose. Our approach is based on the dense extraction of discriminative local descriptors extracted from 2D views. We aggregate the descriptors into a single vector signature using tensor products. The similarity between 3D models can then be efficiently computed with a simple dot product. Experiments on the SHREC12 commonly-used benchmark demonstrate that our approach obtains superior performance in searching for generic shapes.

Published
2013
Full Text
View/download PDF

35. Web scale image retrieval using compact tensor aggregation of visual descriptors

Author

Romain Negrel, Philippe-Henri Gosselin, David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia Indexation and Data Integration (MIDI), and Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)

Subjects
Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image processing, 02 engineering and technology, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, Preprocessor, Computer vision, Tensor, Visual Word, Quantization (image processing), Image retrieval, Soundness, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, Computer Science Applications, Hardware and Architecture, Computer Science::Computer Vision and Pattern Recognition, Signal Processing, Memory footprint, 020201 artificial intelligence & image processing, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Software
Abstract

International audience; The main issues of web scale image retrieval are to achieve a good accuracy while retaining low computational time and memory footprint. In this paper, we propose a compact image signature by aggregating tensors of visual descriptors. Efficient aggregation is achieved by preprocessing the descriptors. Compactness is achieved by projection and quantization of the signatures. We compare our method to other efficient signatures on a 1 million images dataset, and show the soundness of the approach.

Published
2013
Full Text
View/download PDF

36. Classification of Urban Scenes from Geo-referenced Images in Urban Street-View Context

Author

Corina Iovan, David Picard, Nicolas Thome, Matthieu Cord, Modélisation de la croissance et de l'architecture des plantes (DIGIPLANTE), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Mathématiques Appliquées aux Systèmes - EA 4037 (MAS), Ecole Centrale Paris-Ecole Centrale Paris, Multimedia Indexation and Data Integration (MIDI), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Picard, David, Mathématiques Appliquées aux Systèmes - EA 4037 (MAS), Ecole Centrale Paris-Ecole Centrale Paris-Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Matching (statistics), Geographic information system, Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, 0211 other engineering and technologies, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Context (language use), 02 engineering and technology, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 11. Sustainability, Pyramid, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Pyramid (image processing), Visual Word, 021101 geological & geomatics engineering, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Contextual image classification, business.industry, Pattern recognition, Bag-of-words model, 020201 artificial intelligence & image processing, Artificial intelligence, Scale (map), business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; This paper addresses the challenging problem of scene classification in street-view georeferenced images of urban environments. More precisely, the goal of this task is semantic image classification, consisting in predicting in a given image, the presence or absence of a pre-defined class (e.g. shops, vegetation, etc.). The approach is based on the BOSSA representation, which enriches the Bag of Words (BoW) model, in conjunction with the Spatial Pyramid Matching scheme and kernel-based machine learning techniques. The proposed method handles problems that arise in large scale urban environments due to acquisition conditions (static and dynamic objects/pedestrians) combined with the continuous acquisition of data along the vehicle's direction, the varying light conditions and strong occlusions (due to the presence of trees, traffic signs, cars, etc.) giving rise to high intra-class variability. Experiments were conducted on a large dataset of high resolution images collected from two main avenues from the 12th district in Paris and the approach shows promising results.

Published
2012

37. Compact Tensor Based Image Representation for Similarity Search

Author

David Picard, Philippe-Henri Gosselin, Romain Negrel, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), Multimedia Indexation and Data Integration (MIDI), CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA), and Gosselin, Philippe-Henri

Subjects
[INFO.INFO-MM] Computer Science [cs]/Multimedia [cs.MM], Theoretical computer science, business.industry, Nearest neighbor search, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM], 020207 software engineering, Pattern recognition, 02 engineering and technology, Content-based image retrieval, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Automatic image annotation, Digital signature, Image texture, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Visual Word, Artificial intelligence, business, Image retrieval, Feature detection (computer vision), Mathematics
Abstract

International audience; Within the Content Based Image Retrieval (CBIR) frame- work, one of the main challenges is to tackle the scalability issues. We propose a new compact signature for similarity search. We use an original method to perform a high com- pression of signatures while retraining their effectiveness. We propose an embedding method that maps large signatures into a low-dimensional hilbert space. We evaluated the method on Holidays database and compared the results with methods of state-of-the-art.

Published
2012

38. An Application of Swarm Intelligence to Distributed Image Retrieval

Author

Arnaud Revel, Matthieu Cord, David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Laboratoire Informatique, Image et Interaction - EA 2118 (L3I), Université de La Rochelle (ULR), Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), and La Rochelle Université (ULR)

Subjects
Information Systems and Management, Computer science, Relevance feedback, 02 engineering and technology, Machine learning, computer.software_genre, Content-based image retrieval, TRECVID, Theoretical Computer Science, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Artificial Intelligence, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Relevance (information retrieval), Visual Word, Image retrieval, Cognitive models of information retrieval, Information retrieval, business.industry, Computer Science Applications, Control and Systems Engineering, Human–computer information retrieval, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Software
Abstract

International audience; In this article, we introduce an application of swarm intelligence to distributed visual information retrieval distributed over networks. Based on the relevance feedback scheme, we use ant-like agents to crawl the network and to retrieve relevant images. Agents movements are influenced by markers stored on the hosts. These markers are reinforced to match the distribution of relevant images over the network. We tackle the use of the information gathered during previous search sessions. In order to match the different categories available on the network, we use several markers. Sessions searching for the same category will thus use the same makers. The system involves three learning problems: the selection of relevant markers regarding the searched category, the reinforcement of these markers and the learning of the relevance function. All of these problems are based on the relevance feedback loop. We test our system on a custom network hosting images taken from the well known TrecVid dataset. Our system shows a high improvement over classical content based image retrieval systems which do not use previous sessions information.

Published
2012
Full Text
View/download PDF

39. Improving image similarity with vectors of locally aggregated tensors

Author

David Picard, Philippe-Henri Gosselin, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Multimedia Indexation and Data Integration (MIDI), and Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)

Subjects
Contextual image classification, Image classification, business.industry, 020207 software engineering, Pattern recognition, 02 engineering and technology, Content-based image retrieval, Visualization, Kernel method, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Kernel (image processing), Bag-of-words model, Linearization, 0202 electrical engineering, electronic engineering, information engineering, Bag of Words, 020201 artificial intelligence & image processing, Artificial intelligence, business, Image representation, Image retrieval, Mathematics
Abstract

International audience; Within the Content Based Image Retrieval (CBIR) framework, three main points can be highlighted: visual descriptors extraction, image signatures and their associated similarity measures, and machine learning based relevance functions. While the first and the last points have vastly improved in recent years, this paper addresses the second point. We propose a novel approach to compute vector representations extending state of the art methods in the field. Furthermore, our method can be viewed as a linearization of efficient well known kernel methods. The evaluation shows that our representation significantly improve state of the art results on the difficult VOC2007 database by a fair margin.

Published
2011
Full Text
View/download PDF

40. An efficient System for combining complementary kernels in complex visual categorization tasks

Author

Matthieu Cord, Nicolas Thome, David Picard, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), and Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Multiple kernel learning, Contextual image classification, business.industry, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020206 networking & telecommunications, Pattern recognition, 02 engineering and technology, Machine learning, computer.software_genre, Visualization, Kernel (image processing), Categorization, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Histogram, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Spatial analysis, computer, Mathematics
Abstract

International audience; Recently, increasing interest has been brought to improve image categorization performances by combining multiple descriptors. However, very few approaches have been proposed for combining features based on complementary aspects, and evaluating the performances in realistic databases. In this paper, we tackle the problem of combining different feature types (edge and color), and evaluate the performance gain in the very challenging VOC 2009 benchmark. Our contribution is three-fold. First, we propose new local color descriptors, unifying edge and color feature extraction into the "Bag Of Word" model. Second, we improve the Spatial Pyramid Matching (SPM) scheme for better incorporating spatial information into the similarity measurement. Last but not least, we propose a new combination strategy based on ℓ1 Multiple Kernel Learning (MKL) that simultaneously learns individual kernel parameters and the kernel combination. Experiments prove the relevance of the proposed approach, which outperforms baseline combination methods while being computationally effective.

Published
2010
Full Text
View/download PDF

41. Long Term Learning for Image Retrieval over Networks

Author

Matthieu Cord, David Picard, Arnaud Revel, Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), and Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY)

Subjects
Information retrieval, Computer science, Active learning (machine learning), business.industry, Relevance feedback, [SCCO.COMP]Cognitive science/Computer science, 02 engineering and technology, Crawling, Machine learning, computer.software_genre, Content-based image retrieval, 020204 information systems, Similarity (psychology), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Mobile agent, Artificial intelligence, Routing (electronic design automation), business, computer, Image retrieval
Abstract

International audience; In this paper, we present a long term learning system for con- tent based image retrieval over a network. Relevant feedback is used among different sessions to learn both the similarity function and the best routing for the searched category. Our system is based on mobile agents crawling the network in search of relevant images. An ant-behavior algorithm is used to learn the category dependent routing. With experiments on trecvid'05 key-frame dataset, we show that the smart associ- ation of category dependent routing and active learning leads to an improvement of the quality of the retrieval.

Published
2008
Full Text
View/download PDF

42. Image Retrieval over Networks: Ant Algorithm for Long Term Active Learning

Author

David Picard, Matthieu Cord, Arnaud Revel, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY), Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), and Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Information retrieval, Computer science, Active learning (machine learning), business.industry, Relevance feedback, [SCCO.COMP]Cognitive science/Computer science, 02 engineering and technology, Crawling, Content-based image retrieval, Machine learning, computer.software_genre, Session (web analytics), 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Relevance (information retrieval), Artificial intelligence, Routing (electronic design automation), business, Image retrieval, computer
Abstract

International audience; Image retrieval over a network is the focus of this paper, as being a major challenge of content based image retrieval. We present a system that gathers feedbacks given by the users in order to learn the location of the searched images. As a result, the active learning of a content based relevance function is enhanced by the selection of hosts containing relevant examples. We achieve a long term merging of feedbacks over many sessions, without any knowledge about the category being searched at any session. Our system is based on mobile agents crawling the network in an ant-like behavior. Markers are used to learn a routing of the agent leading them to the relevant images. The benefits of the ant-like agents system is a natural parallelization of the processing as well as a distributed approach to the routing learning. We made experiments on the trecvidpsila05 key-frame dataset showing that the location of the categories were efficiently learned. Furthermore, the long-term learning of categories improves the interaction by reducing the number of labels needed during the interaction to obtain satisfying results.

Published
2008
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results