Search

Your search keyword '"Pinz, Axel"' showing total 644 results
Start Over Author "Pinz, Axel"

Refine your results

more »

more »

more »

more »
644 results on '"Pinz, Axel"'

1. Synthesizing human-like sketches from natural images using a conditional convolutional decoder

Author

Kampelmühler, Moritz and Pinz, Axel

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Humans are able to precisely communicate diverse concepts by employing sketches, a highly reduced and abstract shape based representation of visual content. We propose, for the first time, a fully convolutional end-to-end architecture that is able to synthesize human-like sketches of objects in natural images with potentially cluttered background. To enable an architecture to learn this highly abstract mapping, we employ the following key components: (1) a fully convolutional encoder-decoder structure, (2) a perceptual similarity loss function operating in an abstract feature space and (3) conditioning of the decoder on the label of the object that shall be sketched. Given the combination of these architectural concepts, we can train our structure in an end-to-end supervised fashion on a collection of sketch-image pairs. The generated sketches of our architecture can be classified with 85.6% Top-5 accuracy and we verify their visual quality via a user study. We find that deep features as a perceptual similarity metric enable image translation with large domain gaps and our findings further show that convolutional neural networks trained on image classification tasks implicitly learn to encode shape information. Code is available under https://github.com/kampelmuehler/synthesizing_human_like_sketches, Comment: In IEEE Winter Conference on Applications of Computer Vision (WACV) 2020

Published
2020

2. What have we learned from deep representations for action recognition?

Author

Feichtenhofer, Christoph, Pinz, Axel, Wildes, Richard P., and Zisserman, Andrew

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal representations by visualizing what two-stream models have learned in order to recognize actions in video. We show that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions. Key observations include the following. First, cross-stream fusion enables the learning of true spatiotemporal features rather than simply separate appearance and motion features. Second, the networks can learn local representations that are highly class specific, but also generic representations that can serve a range of classes. Third, throughout the hierarchy of the network, features become more abstract and show increasing invariance to aspects of the data that are unimportant to desired distinctions (e.g. motion patterns across various speeds). Fourth, visualizations can be used not only to shed light on learned representations, but also to reveal idiosyncracies of training data and to explain failure cases of the system., Comment: This document is best viewed in Adobe Reader where figures play on click. Supplementary material can be downloaded at http://feichtenhofer.github.io/action_vis.pdf

Published
2018

3. Detect to Track and Track to Detect

Author

Feichtenhofer, Christoph, Pinz, Axel, and Zisserman, Andrew

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs detection and tracking, solving the task in a simple and effective way. Our contributions are threefold: (i) we set up a ConvNet architecture for simultaneous detection and tracking, using a multi-task objective for frame-based object detection and across-frame track regression; (ii) we introduce correlation features that represent object co-occurrences across time to aid the ConvNet during tracking; and (iii) we link the frame level detections based on our across-frame tracklets to produce high accuracy detections at the video level. Our ConvNet architecture for spatiotemporal object detection is evaluated on the large-scale ImageNet VID dataset where it achieves state-of-the-art results. Our approach provides better single model performance than the winning method of the last ImageNet challenge while being conceptually much simpler. Finally, we show that by increasing the temporal stride we can dramatically increase the tracker speed., Comment: ICCV 2017. Code and models: https://github.com/feichtenhofer/Detect-Track Results: https://www.robots.ox.ac.uk/~vgg/research/detect-track/

Published
2017

4. Spatiotemporal Residual Networks for Video Action Recognition

Author

Feichtenhofer, Christoph, Pinz, Axel, and Wildes, Richard P.

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we introduce spatiotemporal ResNets as a combination of these two approaches. Our novel architecture generalizes ResNets for the spatiotemporal domain by introducing residual connections in two ways. First, we inject residual connections between the appearance and motion pathways of a two-stream architecture to allow spatiotemporal interaction between the two streams. Second, we transform pretrained image ConvNets into spatiotemporal networks by equipping these with learnable convolutional filters that are initialized as temporal residual connections and operate on adjacent feature maps in time. This approach slowly increases the spatiotemporal receptive field as the depth of the model increases and naturally integrates image ConvNet design principles. The whole model is trained end-to-end to allow hierarchical learning of complex spatiotemporal features. We evaluate our novel spatiotemporal ResNet using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art., Comment: NIPS 2016

Published
2016

5. Convolutional Two-Stream Network Fusion for Video Action Recognition

Author

Feichtenhofer, Christoph, Pinz, Axel, and Zisserman, Andrew

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse such networks spatially at the last convolutional layer than earlier, and that additionally fusing at the class prediction layer can boost accuracy; finally (iii) that pooling of abstract convolutional features over spatiotemporal neighbourhoods further boosts performance. Based on these studies we propose a new ConvNet architecture for spatiotemporal fusion of video snippets, and evaluate its performance on standard benchmarks where this architecture achieves state-of-the-art results., Comment: in Proc. CVPR 2016

Published
2016

6. Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data

Author

Brkić, Karla, Rašić, Srđan, Pinz, Axel, Šegvić, Siniša, and Kalafatić, Zoran

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors of space-time, suitable for building a partial representation of arbitrary spatio-temporal phenomena. Because of the possibility of iterative refinement, they are interesting in the context of online human action recognition. We investigate the use of dense optical flow as the image function of the STA descriptor for human action recognition, using two different algorithms for computing the flow: the Farneb\"ack algorithm and the TVL1 algorithm. We provide a detailed analysis of the influencing optical flow algorithm parameters on the produced optical flow fields. An extensive experimental validation of optical flow-based STA descriptors in human action recognition is performed on the KTH human action dataset. The encouraging experimental results suggest the potential of our approach in online human action recognition., Comment: Part of the Proceedings of the Croatian Computer Vision Workshop, CCVW 2013, Year 1

Published
2013

8. Radiometry Propagation to Large 3D Point Clouds from Sparsely Sampled Ground Truth

Author

Höll, Thomas, Pinz, Axel, 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, Chen, Chu-Song, editor, Lu, Jiwen, editor, and Ma, Kai-Kuang, editor

Published
2017
Full Text
View/download PDF

9. Graph-Based Shape Similarity of Petroglyphs

Author

Seidl, Markus, Wieser, Ewald, Zeppelzauer, Matthias, Pinz, Axel, Breiteneder, Christian, 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, Agapito, Lourdes, editor, Bronstein, Michael M., editor, and Rother, Carsten, editor

Published
2015
Full Text
View/download PDF

10. A Boundary-Fragment-Model for Object Detection

Author

Opelt, Andreas, Pinz, Axel, Zisserman, Andrew, 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, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Dough, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Leonardis, Aleš, editor, Bischof, Horst, editor, and Pinz, Axel, editor

Published
2006
Full Text
View/download PDF

13. Towards Space-Time Semantics in Two Frames

Author

Brkić, Karla, Pinz, Axel, Kalafatić, Zoran, Šegvić, Siniša, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Fusiello, Andrea, editor, Murino, Vittorio, editor, and Cucchiara, Rita, editor

Published
2012
Full Text
View/download PDF

14. Mobile Surveillance by 3D-Outlier Analysis

Author

Holzer, Peter, Pinz, Axel, 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, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Koch, Reinhard, editor, and Huang, Fay, editor

Published
2011
Full Text
View/download PDF

15. Histogram-Based Description of Local Space-Time Appearance

Author

Brkić, Karla, Pinz, Axel, Šegvić, Siniša, Kalafatić, Zoran, 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, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Heyden, Anders, editor, and Kahl, Fredrik, editor

Published
2011
Full Text
View/download PDF

17. On-Line, Incremental Learning of a Robust Active Shape Model

Author

Fussenegger, Michael, Roth, Peter M., Bischof, Horst, Pinz, Axel, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Franke, Katrin, editor, Müller, Klaus-Robert, editor, Nickolay, Bertram, editor, and Schäfer, Ralf, editor

Published
2006
Full Text
View/download PDF

18. Multiregion Level Set Tracking with Transformation Invariant Shape Priors

Author

Fussenegger, Michael, Deriche, Rachid, Pinz, Axel, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Narayanan, P. J., editor, Nayar, Shree K., editor, and Shum, Heung-Yeung, editor

Published
2006
Full Text
View/download PDF

19. A Multiphase Level Set Based Segmentation Framework with Pose Invariant Shape Priors

Author

Fussenegger, Michael, Deriche, Rachid, Pinz, Axel, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Narayanan, P. J., editor, Nayar, Shree K., editor, and Shum, Heung-Yeung, editor

Published
2006
Full Text
View/download PDF

20. Object Localization with Boosting and Weak Supervision for Generic Object Recognition

Author

Opelt, Andreas, Pinz, Axel, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Kalviainen, Heikki, editor, Parkkinen, Jussi, editor, and Kaarna, Arto, editor

Published
2005
Full Text
View/download PDF

23. Epilog

Author

Pinz, Axel, Schildt, Gerhard-Helge, editor, and Pinz, Axel

Published
1994
Full Text
View/download PDF

29. An AR Human Computer Interface for Object Localization in a Cognitive Vision Framework

Author

Siegl, Hannes, Schweighofer, Gerald, Pinz, Axel, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Sebe, Nicu, editor, Lew, Michael, editor, and Huang, Thomas S., editor

Published
2004
Full Text
View/download PDF

31. Real-Time Camera Pose in a Room

Author

Chandraker, Manmohan Krishna, Stock, Christoph, Pinz, Axel, Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Crowley, James L., editor, Piater, Justus H., editor, Vincze, Markus, editor, and Paletta, Lucas, editor

Published
2003
Full Text
View/download PDF

37. A Vision Driven Automatic Assembly Unit

Author

Bachler, Gernot, Berger, Martin, Röhrer, Reinhard, Scherer, Stefan, Pinz, Axel, Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Solina, Franc, editor, and Leonardis, Alešs, editor

Published
1999
Full Text
View/download PDF

44. Robust pose estimation from a planar target

Author

Schweighofer, Gerald and Pinz, Axel

Subjects
Error functions -- Analysis, Cameras -- Design and construction, Estimation theory -- Analysis
Abstract

In theory, the pose of a calibrated camera can be uniquely determined from a minimum of four coplanar but noncollinear points. In practice, there are many applications of camera pose tracking from planar targets and there is also a number of recent pose estimation algorithms which perform this task in real-time, but all of these algorithms suffer from pose ambiguities. This paper investigates the pose ambiguity for planar targets viewed by a perspective camera. We show that pose ambiguities--two distinct local minima of the according error function--exist even for cases with wide angle lenses and close range targets. We give a comprehensive interpretation of the two minima and derive an analytical solution that locates the second minimum. Based on this solution, we develop a new algorithm for unique and robust pose estimation from a planar target. In the experimental evaluation, this algorithm outperforms four state-of-the-art pose estimation algorithms. Index Terms--Camera pose ambiguity, pose tracking.

Published
2006

45. Generic object recognition with boosting

Author

Opelt, Andreas, Pinz, Axel, Fussenegger, Michael, and Auer, Peter

Subjects
Object recognition (Computers) -- Analysis, Pattern recognition -- Analysis
Abstract

This paper explores the power and the limitations of weakly supervised categorization. We present a complete framework that starts with the extraction of various local regions of either discontinuity or homogeneity. A variety of local descriptors can be applied to form a set of feature vectors for each local region. Boosting is used to learn a subset of such feature vectors (weak hypotheses) and to combine them into one final hypothesis for each visual category. This combination of individual extractors and descriptors leads to recognition rates that are superior to other approaches which use only one specific extractor/descriptor setting. To explore the limitation of our system, we had to set up new, highly complex image databases that show the objects of interest at varying scales and poses, in cluttered background, and under considerable occlusion. We obtain classification results up to 81 percent ROC-equal error rate on the most complex of our databases. Our approach outperforms all comparable solutions on common databases. Index Terms--Boosting, object categorization, object localization.

Published
2006

50. Hybrid tracking for outdoor augmented reality applications

Author

Ribo, Miguel, Lang, Peter, Ganster, Harald, Brandner, Markus, Stock, Christoph, and Pinz, Axel

Subjects
Virtual reality technology, Machine vision -- Research, Computer graphics -- Research, Image processing -- Research, Motion -- Research, Three-dimensional graphics -- Research, Virtual reality -- Research
Published
2002

Catalog

Books, media, physical & digital resources
See catalog results