cvpr cvpr2013 cvpr2013-335 cvpr2013-335-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Leonid Pishchulin, Mykhaylo Andriluka, Peter Gehler, Bernt Schiele
Abstract: In this paper we consider the challenging problem of articulated human pose estimation in still images. We observe that despite high variability of the body articulations, human motions and activities often simultaneously constrain the positions of multiple body parts. Modelling such higher order part dependencies seemingly comes at a cost of more expensive inference, which resulted in their limited use in state-of-the-art methods. In this paper we propose a model that incorporates higher order part dependencies while remaining efficient. We achieve this by defining a conditional model in which all body parts are connected a-priori, but which becomes a tractable tree-structured pictorial structures model once the image observations are available. In order to derive a set of conditioning variables we rely on the poselet-based features that have been shown to be effective for people detection but have so far found limited application for articulated human pose estimation. We demon- strate the effectiveness of our approach on three publicly available pose estimation benchmarks improving or being on-par with state of the art in each case.
[1] A. Agarwal and B. Triggs. Recovering 3D human pose from monocular images. PAMI’02. 3
[2] M. Andriluka, S. Roth, and B. Schiele. Discriminative appearance models for pictorial structures. IJCV’11. 1, 3, 4
[3] M. Andriluka, S. Roth, and B. Schiele. Pictorial structures revisited: People detection and articulated pose estimation. In CVPR, 2009. 2, 3, 4, 5, 6, 7, 8
[4] L. Bourdev, S. Maji, T. Brox, and J. Malik. Detecting people using mutually consistent poselet activations. In ECCV, 2010. 1
[5] L. Bourdev and J. Malik. Poselets: Body part detectors trained using 3D human pose annotations. In ICCV’09. 4
[6] L. Clemmensen, T. Hastie, D. Witten, and B. Ersbll. Sparse discriminant analysis. Technometrics, 2011. 4
[7] C. Desai and D. Ramanan. Detecting actions, poses, and objects with relational phraselets. In ECCV, 2012. 2
[8] K. Duan, D. Batra, and D. Crandall. A multi-layer composite model for human pose estimation. In In BMVC’12. 7
[9] M. Eichner and V. Ferrari. Appearance sharing for collective human pose estimation. In In ACCV’12. 5, 6
[10] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained partbased models. PAMI’10. 1, 3
[11] P. F. Felzenszwalb and D. P. Huttenlocher. Pictorial structures for object recognition. IJCV’05. 1, 3
[12] M. A. Fischler and R. A. Elschlager. The representation and matching of pictorial structures. IEEE Trans. Comput’73. 1
[13] C. Ionescu, F. Li, and C. Sminchisescu. Latent structured models for human pose estimation. In ICCV’11. 3
[14] S. Johnson and M. Everingham. Clustered pose and nonlinear appearance models for human pose estimation. In BMVC’10. 1, 2, 5
[15] S. Johnson and M. Everingham. Learning Effective Human Pose Estimation from Inaccurate Annotation. In CVPR’11. 1, 7
[16] L. Pishchulin, A. Jain, M. Andriluka, T. Thormaehlen, and B. Schiele. Articulated people detection and pose estimation:
[17]
[18]
[19]
[20]
[21]
[22]
[23]
[24]
[25]
[26] Reshaping the future. In CVPR, 2012. 4, 7 D. Ramanan. Learning to parse images of articulated objects. In NIPS’06. 5 G. Rogez, J. Rihan, S. Ramalingam, C. Orrite, and P. H. Torr. Randomized trees for human pose detection. In CVPR ’08. 3 B. Sapp, C. Jordan, and B. Taskar. Adaptive pose priors for pictorial structures. In CVPR ’10. 3 B. Sapp, D. Weiss, and B. Taskar. Parsing human motion with stretchable models. In CVPR, 2011. 1 M. Sun and S. Savarese. Articulated part-based model for joint object detection and pose estimation. In ICCV’11. 1, 2 T.-P. Tian and S. Sclaroff. Fast globally optimal 2d human detection with loopy graph models. In CVPR ’10. 1 D. Tran and D. A. Forsyth. Improved human parsing with a full relational model. In ECCV, 2010. 1, 5 R. Urtasun and T. Darrell. Local probabilistic regression for activity-independent human pose inference. In ICCV’09. 3 Y. Wang, D. Tran, and Z. Liao. Learning hierarchical poselets for human parsing. In CVPR’11. 1, 2, 4, 7, 8 Y. Yang and D. Ramanan. Articulated pose estimation with flexible mixtures-of-parts. In CVPR ’11. 1, 2, 3, 4, 6, 7 555999335