Search

Your search keyword '"Bibi, Adel"' showing total 84 results
Start Over Author "Bibi, Adel"

Refine your results

more »

more »

more »
84 results on '"Bibi, Adel"'

51. TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild

Author

Müller, Matthias, Bibi, Adel, Giancola, Silvio, Al-Subaihi, Salman, and Ghanem, Bernard

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics
Abstract

Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on object detection datasets due to the scarcity of dedicated large-scale tracking datasets. In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild. We provide more than 30K videos with more than 14 million dense bounding box annotations. Our dataset covers a wide selection of object classes in broad and diverse context. By releasing such a large-scale dataset, we expect deep trackers to further improve and generalize. In addition, we introduce a new benchmark composed of 500 novel videos, modeled with a distribution similar to our training dataset. By sequestering the annotation of the test set and providing an online evaluation server, we provide a fair benchmark for future development of object trackers. Deep trackers fine-tuned on a fraction of our dataset improve their performance by up to 1.6% on OTB100 and up to 1.7% on TrackingNet Test. We provide an extensive benchmark on TrackingNet by evaluating more than 20 trackers. Our results suggest that object tracking in the wild is far from being solved., Comment: preprint

Published
2018

52. Gabor Layers Enhance Network Robustness

Author

Pérez, Juan C., Alfarra, Motasem, Jeanneret, Guillaume, Bibi, Adel, Thabet, Ali, Ghanem, Bernard, Arbeláez, Pablo, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Vedaldi, Andrea, editor, Bischof, Horst, editor, Brox, Thomas, editor, and Frahm, Jan-Michael, editor

Published
2020
Full Text
View/download PDF

53. Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress

Author

Prabhu, Ameya, Udandarao, Vishaal, Torr, Philip, Bethge, Matthias, Bibi, Adel, Albanie, Samuel, Prabhu, Ameya, Udandarao, Vishaal, Torr, Philip, Bethge, Matthias, Bibi, Adel, and Albanie, Samuel

Abstract

Standardized benchmarks drive progress in machine learning. However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies. In our work, we seek to mitigate this challenge by compiling ever-expanding large-scale benchmarks called Lifelong Benchmarks. As exemplars of our approach, we create Lifelong-CIFAR10 and Lifelong-ImageNet, containing (for now) 1.69M and 1.98M test samples, respectively. While reducing overfitting, lifelong benchmarks introduce a key challenge: the high cost of evaluating a growing number of models across an ever-expanding sample set. To address this challenge, we also introduce an efficient evaluation framework: Sort \& Search (S&S), which reuses previously evaluated models by leveraging dynamic programming algorithms to selectively rank and sub-select test samples, enabling cost-effective lifelong benchmarking. Extensive empirical evaluations across 31,000 models demonstrate that S&S achieves highly-efficient approximate accuracy measurement, reducing compute cost from 180 GPU days to 5 GPU hours (1000x reduction) on a single A100 GPU, with low approximation error. As such, lifelong benchmarks offer a robust, practical solution to the "benchmark exhaustion" problem.

Published
2024

55. Gabor Layers Enhance Network Robustness

Author

Pérez, Juan C., primary, Alfarra, Motasem, additional, Jeanneret, Guillaume, additional, Bibi, Adel, additional, Thabet, Ali, additional, Ghanem, Bernard, additional, and Arbeláez, Pablo, additional

Published
2020
Full Text
View/download PDF

56. Target Response Adaptation for Correlation Filter Tracking

Author

Bibi, Adel, Mueller, Matthias, Ghanem, Bernard, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Leibe, Bastian, editor, Matas, Jiri, editor, Sebe, Nicu, editor, and Welling, Max, editor

Published
2016
Full Text
View/download PDF

60. Provably Correct Physics-Informed Neural Networks

Author

Eiras, Francisco, Bibi, Adel, Bunel, Rudy, Dvijotham, Krishnamurthy Dj, Torr, Philip, and Kumar, M. Pawan

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, FOS: Physical sciences, Mathematical Physics (math-ph), Mathematical Physics, Machine Learning (cs.LG)
Abstract

Recent work provides promising evidence that Physics-informed neural networks (PINN) can efficiently solve partial differential equations (PDE). However, previous works have failed to provide guarantees on the worst-case residual error of a PINN across the spatio-temporal domain - a measure akin to the tolerance of numerical solvers - focusing instead on point-wise comparisons between their solution and the ones obtained by a solver on a set of inputs. In real-world applications, one cannot consider tests on a finite set of points to be sufficient grounds for deployment, as the performance could be substantially worse on a different set. To alleviate this issue, we establish tolerance-based correctness conditions for PINNs over the entire input domain. To verify the extent to which they hold, we introduce $\partial$-CROWN: a general, efficient and scalable post-training framework to bound PINN residual errors. We demonstrate its effectiveness in obtaining tight certificates by applying it to two classically studied PDEs - Burgers' and Schr\"odinger's equations -, and two more challenging ones with real-world applications - the Allan-Cahn and Diffusion-Sorption equations.

Published
2023

64. SimCS: Simulation for Online Domain-Incremental Continual Segmentation

Author

Alfarra, Motasem, Cai, Zhipeng, Bibi, Adel, Ghanem, Bernard, and Müller, Matthias

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Machine Learning (cs.LG)
Abstract

Continual Learning is a step towards lifelong intelligence where models continuously learn from recently collected data without forgetting previous knowledge. Existing continual learning approaches mostly focus on image classification in the class-incremental setup with clear task boundaries and unlimited computational budget. This work explores Online Domain-Incremental Continual Segmentation~(ODICS), a real-world problem that arises in many applications, \eg, autonomous driving. In ODICS, the model is continually presented with batches of densely labeled images from different domains; computation is limited and no information about the task boundaries is available. In autonomous driving, this may correspond to the realistic scenario of training a segmentation model over time on a sequence of cities. We analyze several existing continual learning methods and show that they do not perform well in this setting despite working well in class-incremental segmentation. We propose SimCS, a parameter-free method complementary to existing ones that leverages simulated data as a continual learning regularizer. Extensive experiments show consistent improvements over different types of continual learning methods that use regularizers and even replay., 13 pages, 5 figures, and 8 tables

Published
2022

67. Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers

Author

Franzmeyer, Tim, McAleer, Stephen, Henriques, João F., Foerster, Jakob N., Torr, Philip H. S., Bibi, Adel, and de Witt, Christian Schroeder

Subjects
FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence
Abstract

Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attacks possible. We demonstrate that existing observation-space attacks on reinforcement learning agents have a common weakness: while effective, their lack of temporal consistency makes them detectable using automated means or human inspection. Detectability is undesirable to adversaries as it may trigger security escalations. We introduce perfect illusory attacks, a novel form of adversarial attack on sequential decision-makers that is both effective and provably statistically undetectable. We then propose the more versatile R-attacks, which result in observation transitions that are consistent with the state-transition function of the adversary-free environment and can be learned end-to-end. Compared to existing attacks, we empirically find R-attacks to be significantly harder to detect with automated methods, and a small study with human subjects suggests they are similarly harder to detect for humans. We propose that undetectability should be a central concern in the study of adversarial attacks on mixed-autonomy settings.

Published
2022
Full Text
View/download PDF

68. Catastrophic overfitting is a bug but also a feature

Author

Ortiz-Jiménez, Guillermo, de Jorge, Pau, Sanyal, Amartya, Bibi, Adel, Dokania, Puneet K., Frossard, Pascal, Rogéz, Gregory, and Torr, Philip H. S.

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Machine Learning (cs.LG)
Abstract

Despite clear computational advantages in building robust neural networks, adversarial training (AT) using single-step methods is unstable as it suffers from catastrophic overfitting (CO): Networks gain non-trivial robustness during the first stages of adversarial training, but suddenly reach a breaking point where they quickly lose all robustness in just a few iterations. Although some works have succeeded at preventing CO, the different mechanisms that lead to this remarkable failure mode are still poorly understood. In this work, however, we find that the interplay between the structure of the data and the dynamics of AT plays a fundamental role in CO. Specifically, through active interventions on typical datasets of natural images, we establish a causal link between the structure of the data and the onset of CO in single-step AT methods. This new perspective provides important insights into the mechanisms that lead to CO and paves the way towards a better understanding of the general dynamics of robust model construction. The code to reproduce the experiments of this paper can be found at https://github.com/gortizji/co_features ., Comment: 24 pages, 19 figures, 1 table. Work partially presented at Adversarial Machine Learning Workshop at ICML 2022

Published
2022
Full Text
View/download PDF

71. On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective

Author

Alfarra, Motasem, Bibi, Adel, Hammoud, Hasan, Gaafar, Mohamed, and Ghanem, Bernard

Abstract

This work tackles the problem of characterizing and understanding the decision boundaries of neural networks with piecewise linear non-linearity activations. We use tropical geometry, a new development in the area of algebraic geometry, to characterize the decision boundaries of a simple network of the form (Affine, ReLU, Affine). Our main finding is that the decision boundaries are a subset of a tropical hypersurface, which is intimately related to a polytope formed by the convex hull of two zonotopes. The generators of these zonotopes are functions of the network parameters. This geometric characterization provides new perspectives to three tasks. (i) We propose a new tropical perspective to the lottery ticket hypothesis, where we view the effect of different initializations on the tropical geometric representation of a network's decision boundaries. (ii) Moreover, we propose new tropical based optimization reformulations that directly influence the decision boundaries of the network for the task of network pruning. (iii) At last, we discuss the reformulation of the generation of adversarial attacks in a tropical sense. We demonstrate that one can construct adversaries in a new tropical setting by perturbing a specific set of decision boundaries by perturbing a set of parameters in the network.

Published
2023
Full Text
View/download PDF

73. Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives

Author

Bibi, Adel

Abstract

This dissertation aims at theoretically studying a block of layers that is common in al- most all deep learning models. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation that is followed by another affine layer. We study this block from three perspectives. (i) An Optimization Perspective. Is it possible that the output of the forward pass through this block is an optimal solution to a certain convex optimization problem? We show an equivalency between the forward pass through this block and a single iteration of deterministic and stochastic algorithms solving a ten- sor formulated convex optimization problem. As consequence, we derive for the first time a formula for computing the singular values of convolutional layers surpassing the need for the prohibitive construction of the underlying linear operator. Thereafter, we show that several deep networks can have this block replaced with the corresponding optimiza- tion algorithm predicted by our theory resulting in networks with improved generalization performance. (ii) A Probabilistic Perspective. Is it possible to analytically analyze the output of a deep network upon subjecting the input to Gaussian noise? To that regard, we derive analytical formulas for the first and second moments of this block under Gaussian input noise. We demonstrate that the derived expressions can be used to efficiently analyze the output of an arbitrary deep network in addition to constructing Gaussian adversarial attacks surpassing any need for prohibitive data augmentation procedures. (iii) A Tropi- cal Geometry Perspective. Is it possible to characterize the decision boundaries of this block as a geometric structure representing a solution set to a certain class of polynomials (tropical polynomials)? If so, then, is it possible to utilize this geometric representation of the decision boundaries for novel reformulations to classical computer vision and machine learning tasks on arbitrary deep networks? We show that the decision boundaries of this block are a subset of a tropical hypersurface, which is intimately related to a the polytope that is the convex hull of two zonotopes. We utilize this geometric characterization to shed lights on new perspectives of network pruning.

Published
2020
Full Text
View/download PDF

74. TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild

Author

M��ller, Matthias, Bibi, Adel, Giancola, Silvio, Al-Subaihi, Salman, and Ghanem, Bernard

Subjects
FOS: Computer and information sciences, Computer Science - Robotics, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Robotics (cs.RO)
Abstract

Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on object detection datasets due to the scarcity of dedicated large-scale tracking datasets. In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild. We provide more than 30K videos with more than 14 million dense bounding box annotations. Our dataset covers a wide selection of object classes in broad and diverse context. By releasing such a large-scale dataset, we expect deep trackers to further improve and generalize. In addition, we introduce a new benchmark composed of 500 novel videos, modeled with a distribution similar to our training dataset. By sequestering the annotation of the test set and providing an online evaluation server, we provide a fair benchmark for future development of object trackers. Deep trackers fine-tuned on a fraction of our dataset improve their performance by up to 1.6% on OTB100 and up to 1.7% on TrackingNet Test. We provide an extensive benchmark on TrackingNet by evaluating more than 20 trackers. Our results suggest that object tracking in the wild is far from being solved., preprint

Published
2018

77. Advances in RGB and RGBD Generic Object Trackers

Author

Bibi, Adel

Subjects
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Abstract

Visual object tracking is a classical and very popular problem in computer vision with a plethora of applications such as vehicle navigation, human computer interface, human motion analysis, surveillance, auto-control systems and many more. Given the initial state of a target in the first frame, the goal of tracking is to predict states of the target over time where the states describe a bounding box covering the target. Despite numerous object tracking methods that have been proposed in recent years [1-4], most of these trackers suffer a degradation in performance mainly because of several challenges that include illumination changes, motion blur, complex motion, out of plane rotation, and partial or full occlusion, while occlusion is usually the most contributing factor in degrading the majority of trackers, if not all of them. This thesis is devoted to the advancement of generic object trackers tackling different challenges through different proposed methods. The work presented propose four new state-of-the-art trackers. One of which is 3D based tracker in a particle filter framework where both synchronization and registration of RGB and depth streams are adjusted automatically, and three works in correlation filters that achieve state-of-the-art performance in terms of accuracy while maintaining reasonable speeds.

Published
2016
Full Text
View/download PDF

80. The Visual Object Tracking VOT2015 Challenge Results

Author

Kristan, Matej, Matas, Jiri, Leonardis, Aleš, Felsberg, Michael, Cehovin, Luka, Fernández, Gustavo, Vojir, Tomas, Häger, Gustav, Nebehay, Georg, Pflugfelder, Roman, Gupta, Abhinav, Bibi, Adel, Lukežič, Alan, Garcia-Martin, Alvaro, Saffari, Amir, Petrosino, Alfredo, Montero, Andrés, Varfolomieiev, Anton, Baskurt, Atilla, Zhao, Baojun, Ghanem, Bernard, Martinez, Brais, Lee, Byeongju, Han, Bohyung, Wang, Chaohui, Garcia, Christophe, Zhang, Chunyuan, Schmid, Cordelia, Tao, Dacheng, Kim, Daijin, Huang, Dafei, Prokhorov, Danil, Du, Dawei, Yeung, Dit-Yan, Ribeiro, Eraldo, Shahbaz Khan, Fahad, Porikli, Fatih, Bunyak, Filiz, Zhu, Gao, Seetharaman, Guna, Kieritz, Hilke, Yau, Hing, Li, Hongdong, Qi, Honggang, Bischof, Horst, Possegger, Horst, Lee, Hyemin, Nam, Hyeonseob, Bogun, Ivan, Jeong, Jae-Chan, Cho, Jae-Il, Lee, Jae-Yeong, Zhu, Jianke, Shi, Jianping, Li, Jiatong, Jia, Jiaya, Feng, Jiayi, Gao, Jin, Choi, Jin Young, Kim, Ji-Wan, Lang, Jochen, Martinez, Jose M., Choi, Jongwon, Xing, Junliang, Xue, Kai, Palaniappan, Kannappan, Lebeda, Karel, Alahari, Karteek, Gao, Ke, Yun, Kimin, Wong, Kin Hong, Luo, Lei, Ma, Liang, Ke, Lipeng, Wen, Longyin, Bertinetto, Luca, Pootschi, Mahdieh, Maresca, Mario, Danelljan, Martin, Wen, Mei, Zhang, Mengdan, Arens, Michael, Valstar, Michel, Tang, Ming, Chang, Ming-Ching, Khan, Muhammad, Fan, Nana, Wang, Naiyan, Miksik, Ondrej, Torr, Philip H. S., Wang, Qiang, Martin-Nieto, Rafael, Pelapur, Rengarajan, Bowden, Richard, Laganière, Robert, Moujtahid, Salma, Hare, Sam, Hadfield, Simon, Lyu, Siwei, Li, Siyi, Zhu, Song-Chun, Becker, Stefan, Duffner, Stefan, Hicks, Stephen, Golodetz, Stuart, Choi, Sunglok, Wu, Tianfu, Mauthner, Thomas, Pridmore, Tony, Hu, Weiming, Hübner, Wolfgang, Wang, Xiaomeng, Li, Xin, Shi, Xinchu, Zhao, Xu, Mei, Xue, Shizeng, Yao, Hua, Yang, Li, Yang, Lu, Yang, Li, Yuezun, Chen, Zhaoyun, Huang, Zehua, Chen, Zhe, Zhang, Zhe, He, Zhenyu, Hong, Zhibin, Duffner, Stefan, University of Ljubljana, Czech Technical University in Prague (CTU), University of Birmingham [Birmingham], Linköping University (LIU), Austrian Institute of Technology [Vienna] (AIT), Carnegie Mellon University [Pittsburgh] (CMU), King Abdullah University of Science and Technology (KAUST), Universidad Autónoma de Madrid (UAM), Affectv [London], Università degli Studi di Napoli 'Parthenope' = University of Naples (PARTHENOPE), University of Ottawa [Ottawa], National Technical University of Ukraine 'Kyiv Polytechnic Institute' [Kiev], Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Beijing Institute of Technology (BIT), Faculty of Engineering [Nottingham], University of Nottingham, UK (UON), Seoul National University [Seoul] (SNU), Pohang University of Science and Technology (POSTECH), Université Paris-Est (UPE), National University of Defense Technology [China], Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), University of Technology Sydney (UTS), National Key Laboratory for Parallel and Distributed Processing [Changsha], Toyota Research Institute, Chinese Academy of Sciences [Changchun Branch] (CAS), University at Albany [SUNY], State University of New York (SUNY), Hong Kong University of Science and Technology (HKUST), Florida Institute of Technology [Melbourne], Australian National University (ANU), Networks Research Group (NICTA), National ICT Australia Ltd, University of Missouri [Columbia] (Mizzou), University of Missouri System, Naval Research Laboratory (NRL), Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (Fraunhofer IOSB), Fraunhofer (Fraunhofer-Gesellschaft), The Chinese University of Hong Kong [Hong Kong], Centre of Excellence for Robotic Vision [Canberra], Australian Research Council [Canberra] (ARC), Graz University of Technology [Graz] (TU Graz), Electronics and Telecommunications Research Institute [DaeJeon] (ETRI), Zhejiang University, Institute of Automation - Chinese Academy of Sciences, Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision (LAMSADE), Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Department of Electrical Engineering [Korea Advanced Institute of Science and Technology] (KAIST), Korea Advanced Institute of Science and Technology (KAIST), Centre Maurice Halbwachs (CMH), École des hautes études en sciences sociales (EHESS)-Centre National de la Recherche Scientifique (CNRS)-Département de Sciences sociales ENS-PSL, École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Harbin Engineering University (HRBEU), University of Surrey (UNIS), University of Oxford, Harbin Institute of Technology (HIT), Obvious Enginerring, Laboratoire de Physique Corpusculaire - Clermont-Ferrand (LPC), Université Blaise Pascal - Clermont-Ferrand 2 (UBP)-Institut National de Physique Nucléaire et de Physique des Particules du CNRS (IN2P3)-Centre National de la Recherche Scientifique (CNRS), University of California [Los Angeles] (UCLA), University of California (UC), Laboratoire Interfaces et Systèmes Electrochimiques (LISE), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), Electronics and Telecommunications Research Institute, Rice University [Houston], University of New Orleans, National Key Laboratory of Crop Genetic Improvement, Sichuan University, College of Life Sciences-Huazhong Agricultural University [Wuhan] (HZAU), Key Laboratory for Anisotropy and Texture of Materials, Northeastern University [Shenyang], Institut de minéralogie, de physique des matériaux et de cosmochimie (IMPMC), Muséum national d'Histoire naturelle (MNHN)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de recherche pour le développement [IRD] : UR206-Centre National de la Recherche Scientifique (CNRS), School of Materials Science and Engineering, Shanghai University, State Key Laboratory of Marine Geology [Shanghai], Tongji University, UAM. Departamento de Tecnología Electrónica y de las Comunicaciones, Tratamiento e Interpretación de Vídeo (ING EPS-006), Universidad Autonoma de Madrid (UAM), Universita degli studi di Napoli 'Parthenope' [Napoli], Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), Centre National de la Recherche Scientifique (CNRS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Centre National de la Recherche Scientifique (CNRS)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Université Joseph Fourier - Grenoble 1 (UJF)-Université Pierre Mendès France - Grenoble 2 (UPMF), 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)-Centre National de la Recherche Scientifique (CNRS), University of Oxford [Oxford], University of California, The University of New Orleans, Sichuan University, College of Life Sciences-Huazhong Agricultural University, and Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut de recherche pour le développement [IRD] : UR206-Muséum national d'Histoire naturelle (MNHN)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Computer science, Target tracking, Signalbehandling, 02 engineering and technology, Object tracking, Tracking (particle physics), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Image processing, Datorseende och robotik (autonoma system), 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Computer Vision and Robotics (Autonomous Systems), Visualization, Benchmark testing, Telecomunicaciones, business.industry, Tracking, Australia, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, Object (computer science), Area measurement, Benchmarking, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], Performance evaluation, Video tracking, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, 020201 artificial intelligence & image processing, Artificial intelligence, Radiologi och bildbehandling, business, Flow visualization, Radiology, Nuclear Medicine and Medical Imaging
Abstract

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. M. Kristan et al., "The Visual Object Tracking VOT2015 Challenge Results," 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), Santiago, 2015, pp. 564-586. doi: 10.1109/ICCVW.2015.79, The Visual Object Tracking challenge 2015, VOT2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 62 trackers are presented. The number of tested trackers makes VOT 2015 the largest benchmark on shortterm tracking to date. For each participating tracker, a short description is provided in the appendix. Features of the VOT2015 challenge that go beyond its VOT2014 predecessor are: (i) a new VOT2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute, (ii) extensions of the VOT2014 evaluation methodology by introduction of a new performance measure. The dataset, the evaluation kit as well as the results are publicly available at the challenge website.

Published
2015
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results