Part-Pair Representation for Part Localization
详细信息 查看全文
- 作者：Jiongxin Liu (19)
Yinxiao Li (19)
Peter N. Belhumeur (19) - 关键词：part localization ; part ; pair representation ; pose estimation
- 刊名：Lecture Notes in Computer Science
- 出版年：2014
- 出版时间：2014
- 年：2014
- 卷：8690
- 期：1
- 页码：456-471
- 全文大小：2,264 KB
- 参考文献：1. Amberg, B., Vetters, T.: Optimal landmark detection using shape models and branch and bound. In: Proc. ICCV (2011)
2. Azizpour, H., Laptev, I.: Object detection using strongly-supervised deformable part models. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol.聽7572, pp. 836鈥?49. Springer, Heidelberg (2012) CrossRef
3. Belhumeur, P.N., Jacobs, D.W., Kriegman, D.J., Kumar, N.: Localizing parts of faces using a consensus of exemplars. In: Proc. CVPR (2011)
4. Berg, T., Belhumeur, P.N.: POOF: Part-based one-vs-one features for fine-grained categorization, face verification, and attribute estimation. In: Proc. CVPR (2013)
5. Bourdev, L., Maji, S., Brox, T., Malik, J.: Detecting people using mutually consistent poselet activations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol.聽6316, pp. 168鈥?81. Springer, Heidelberg (2010) CrossRef
6. Branson, S., Beijbom, O., Belongie, S.: Efficient large-scale structured learning. In: Proc. CVPR (2013)
7. Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. In: Proc. CVPR (2012)
8. Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., Yuille, A.: Detect what you can: Detecting and representing objects using holistic models and body parts. In: Proc. CVPR (2014)
9. Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE TPAMI (2001)
10. Cristinacce, D., Cootes, T.: Feature detection and tracking with constrained local models. In: Proc. BMVC (2006)
11. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR (2005)
12. Doll谩r, P.: Piotr鈥檚 Image and Video Matlab Toolbox (PMT), http://vision.ucsd.edu/~pdollar/toolbox/doc/index.html
13. Doll谩r, P., Appel, R., Kienzle, W.: Crosstalk cascades for frame-rate pedestrian detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol.聽7573, pp. 645鈥?59. Springer, Heidelberg (2012) CrossRef
14. Doll谩r, P., Belongie, S., Perona, P.: The fastest pedestrian detector in the west. In: Proc. BMVC (2010)
15. Doll谩r, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: Proc. BMVC (2009)
16. Everingham, M., Sivic, J., Zisserman, A.: 鈥淗ello! my name is... buffy鈥?automatic naming of characters in tv video. In: Proc. BMVC (2006)
17. Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. In: IEEE TPAMI (2010)
18. Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV聽61(1), 55鈥?9 (2005) CrossRef
19. Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: Proc. BMVC (2010)
20. Liu, J., Belhumeur, P.N.: Bird part localization using exemplar-based models with enforced pose and subcategory consistency. In: Proc. ICCV (2013)
21. Matthews, I., Baker, S.: Active appearance models revisited. In: IJCV (2004)
22. Milborrow, S., Nicolls, F.: Locating facial features with an extended active shape model. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol.聽5305, pp. 504鈥?13. Springer, Heidelberg (2008) CrossRef
23. Ouyang, W., Wang, X.: Joint deep learning for pedestrian detection. In: Proc. ICCV (2013)
24. Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Poselet conditioned pictorial structures. In: Proc. CVPR (2013)
25. Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Strong appearance and expressive spatial models for human pose estimation. In: Proc. ICCV (2013)
26. Ramanan, D.: Learning to parse images of articulated bodies. In: Proc. NIPS (2006)
27. Ren, X., Ramanan, D.: Histograms of sparse codes for object detection. In: Proc. CVPR (2013)
28. Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol.聽7573, pp. 73鈥?6. Springer, Heidelberg (2012) CrossRef
29. Sun, M., Savarese, S.: Articulated part-based model for joint object detection and pose estimation. In: Proc. ICCV (2011)
30. Szegedy, C., Toshev, A., Erhan, D.: Deep neural networks for object detection. In: Proc. NIPS (2013)
31. Viola, P., Jones, M.: Robust real-time object detection. IJCV聽57(2), 137鈥?54 (2001) CrossRef
32. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset. Computation & Neural Systems Technical Report, CNS-TR-2011-001 (2011)
33. Wang, Y., Tran, D., Liao, Z.: Learning hierarchical poselets for human parsing. In: Proc. CVPR (2011)
34. Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: Proc. CVPR (2011)
35. Zhou, F., Brandt, J., Lin, Z.: Exemplar-based graph matching for robust facial landmark localization. In: Proc. ICCV (2013)
36. Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: Proc. CVPR (2012) - 作者单位：Jiongxin Liu (19)
Yinxiao Li (19)
Peter N. Belhumeur (19)
19. Columbia University, USA - ISSN：1611-3349
文摘
In this paper, we propose a novel part-pair representation for part localization. In this representation, an object is treated as a collection of part pairs to model its shape and appearance. By changing the set of pairs to be used, we are able to impose either stronger or weaker geometric constraints on the part configuration. As for the appearance, we build pair detectors for each part pair, which model the appearance of an object at different levels of granularities. Our method of part localization exploits the part-pair representation, featuring the combination of non-parametric exemplars and parametric regression models. Non-parametric exemplars help generate reliable part hypotheses from very noisy pair detections. Then, the regression models are used to group the part hypotheses in a flexible way to predict the part locations. We evaluate our method extensively on the dataset CUB-200-2011 [32], where we achieve significant improvement over the state-of-the-art method on bird part localization. We also experiment with human pose estimation, where our method produces comparable results to existing works.