Learning to detect Motion Boundaries

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volumn 07-12-June-2015, Issue , 2015, Pages 2578-2586

  Weinzaepfel, Philippe ^a   Revaud, Jerome ^a   Harchaoui, Zaid ^a,b   Schmid, Cordelia ^a  

^a INRIA   (France)

^b NEW YORK UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER VISION; DECISION TREES; OPTICAL FLOWS; PATTERN RECOGNITION;

COMPUTATIONALLY EFFICIENT; LEARNING-BASED APPROACH; MOTION BOUNDARY; OPTICAL FLOW ALGORITHM; OPTICAL FLOW ESTIMATION; REAL WORLD VIDEOS; STATE OF THE ART; STATE-OF-THE-ART ALGORITHMS;

MOTION ESTIMATION;

EID: 84959185561     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CVPR.2015.7298873     Document Type: Conference Paper

References (37)

1. P. Arbelaez, M. Maire, C. Fowlkes, and 1. Malik. Contour detection and hierarchical image segmentation. IEEE Trans. PAMI, 2011
2. S. B aker and I. Matthews. Lucas-Kanade 20 years on: A unifying framework. IJCV,2004
3. S. B aker, D. Scharstein, 1. P. Lewis, S. Roth, M. 1. B lack, and R. Szeliski. A database and evaluation methodology for optical flow. llCV, 2011
4. S. T. B irchfield. Depth and motion discontinuities. PhD thesis, Stanford University, 1999
5. M. 1. B lack and D. 1. Fleet. Probabilistic detection and tracking of motion boundaries. IJCV,2000. 1,2
6. T. B rox, A. B ruhn, N. Papenberg, and 1. Weickert. High accuracy optical flow estimation based on a theory for warping. In ECCV, 2004
7. T. Brox, A. B ruhn, and J. Weickert. Variational motion segmentation with level sets. In ECCV. 2006
8. T. B rox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. PAMI, 2011
9. A. B ruhn, 1. Weickert, C. Feddern, T. Kohlberger, and C. Schnorr. Variational optical flow computation in real time. IEEE Trans. on Image Processing, 2005
10. D. J. B utler, 1. Wulff, G. B. Stanley, and M. J. B lack. A naturalistic open source movie for optical flow evaluation. In ECCV, 2012. 2,4,7
11. T. Darrell and A. Pentland. Cooperative robust estimation using layers of support. IEEE Trans. PAMI, 1995
12. P. Dollar and C. L. Zitnick. Structured forests for fast edge detection. In ICCV, 2013. 2, 3, 6, S
13. G. Farneback. Two-frame motion estimation based on polynomial expansion. In Scandinavian conference on Image analysis, 2003
14. D. J. Fleet, M. 1. B lack, Y. Yacoob, and A. D. Jepson. Design and use of linear models for image motion analysis. llCV, 2000
15. L. Gorelick, M. B lank, E. Shechtman, M. Irani, and R. B asri. Actions as space-time shapes. IEEE Trans. PAMI, 2007
16. D. Hoiem, A. Efros, and M. Hebert. Recovering occlusion boundaries from an image. llCV, 2011
17. A. Humayun, O. Mac Aodha, and G. 1. B rostow. Learning to Find Occlusion Regions. In CVPR, 2011
18. A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, and L. Fei-Fei. Large-scale video classification with convolutional neural networks. In CVPR, 2014
19. I. Laptev and P. Perez. Retrieving actions in movies. In ICCV, 2007
20. C. Liu, W. T. Freeman, and E. H. Adelson. Analysis of contour motions. In Advances in Neural Information Processing Systems, 2006
21. D. Martin, C. Fowlkes, D. Tal, and 1. Malik. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In ICCV, 2001
22. M. Middendorf and H. Nagel. Estimation and interpretation of discontinuities in optical flow fields. In ICCV, 2001
23. P. Nillius, 1. Sullivan, and S. Carlsson. Multi-target tracking-linking identities using B ayesian network inference. In CVPR, 2006
24. A. Papazoglou and V. Ferrari. Fast object segmentation in unconstrained video. In ICCV, 2013. 1,2
25. A. Prest, C. Leistner, J. Civera, C. Schmid, and V. Ferrari. Learning object class detectors from weakly annotated video. In CVPR, 2012
26. A. Spoerri. The Early Detection of Motion Boundaries. PhD thesis. Massachusetts Institute of Technology, Department of B rain and Cognitive Sciences, 1991
27. A. Stein and M. Hebert. Occlusion boundaries from motion: Low-level detection and mid-level reasoning. llCV, 2009
28. D. Sun, S. Roth, and M. B lack. A quantitative analysis of current practices in optical flow estimation and the principles behind them. llCV, 2014.
29. D. Sun, J. Wulff, E. B. Sudderth, H. Pfister, and M. 1. B lack. A fully-connected layered model of foreground and background flow. In CVPR, 2013
30. P. Sundberg, T. B rox, M. Maire, P. Arbelaez, and J. Malik. Occlusion boundary detection and figure/ground assignment from optical flow. In CVPR, 2011
31. M. Unger, M. Werlberger, T. Pock, and H. B ischof. 10int motion estimation and segmentation of complex scenes with label costs and occlusion modeling. In CVPR, 2012
32. C. Vogel, S. Roth, and K. Schindler. An evaluation of data costs for optical flow. In GCPR, 2013
33. S. Volz, A. B ruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. In ICCV, 2011
34. H. Wang, A. Klaser, c. Schmid, and c.-L. Liu. Dense trajectories and motion boundary descriptors for action recognition. IJCV, 2013. 1,2
35. J. Wang and E. Adelson. Representing moving images with layers. IEEE Trans. Image Processing, 1994
36. P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. Deepflow: Large displacement optical flow with deep matching. In ICCV, 2013
37. C. Zach, T. Pock, and H. Bischof. A duality based approach for realtime tv-II optical flow. Pattern Recognition, 2007.