Handling label noise in video classification via multiple instance learning

Proceedings of the IEEE International Conference on Computer Vision

Volumn , Issue , 2011, Pages 2056-2063

  Leung, Thomas ^a   Song, Yang ^a   Zhang, John ^b  

^a GOOGLE INC   (United States)

^b Columbia University ^*  (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ATTRACTIVE SOLUTIONS; BINARY CLASSIFIERS; CLASSIFICATION SYSTEM; CLASSIFICATION TASKS; CLASSIFIER PERFORMANCE; MULTIPLE INSTANCE LEARNING; NOISY DATA; REAL-WORLD NOISE; TRAINING DATA; TRAINING SAMPLE; VIDEO CLASSIFICATION;

IMAGE PROCESSING;

ADAPTIVE BOOSTING;

EID: 84863060486     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICCV.2011.6126479     Document Type: Conference Paper

References (31)

1. S. Andrews and T. Hofmann. Multiple-instance learning via disjunctive programming boosting. In In NIPS, 2004. 2
2. B. Babenko, P. Dollár, Z. Tu, and S. Belongie. Simultaneous learning and alignment: Multi-instance and multi-pose learning. In Faces in Real-Life Images, October 2008. 2
3. B. Babenko, M.-H. Yang, and S. Belongie. Visual tracking with online multiple instance learning. In CVPR, 2009. 2
4. T. L. Berg and D. A. Forsyth. Animals on the web. In Proc. CVPR, 2006. 1, 2
5. D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichletallocation. J. of Machine Learning Research, 2003. 2
6. G. Chechik, E. Ie, M. Rehn, S. Bengio, and D. Lyon. Largescale content-based audio retrieval from text queries. In Proceeding of the 1st ACM international conference on Multimedia information retrieval, pages 105-112. ACM, 2008. 4
7. Y. Chen, J. Bi, and J. Z. Wang. Miles: Multiple-instance learning via embedded instance selection. PAMI, 2006. 2
8. N. Dalal and B. Triggs. Histogram of oriented gradients for human detection. In Proc. CVPR, 2005. 4
9. P. Dollár, V. Rabaud, G. Cottrell, and S. Belongie. Behavior recognition via sparse spatio-temporal features. In ICCV'05 Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005. 4
10. R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. Liblinear: A library for large linear classification. J. of Machine Learning Research, 2008. 4
11. R. Fergus, L. Fei-Fei, P. Perona, and A. Zisserman. Learning object categories from google's image search. In Proc. ICCV, 2005. 1, 2, 6
12. R. Fergus, Y.Weiss, and A. Torralba. Semi-supervised learning in gigantic image collections. In NIPS, 2009. 1
13. M. Guillaumin, J. Verbeek, and C. Schmid. Multiple instance metric learning from automatically labeled bags of faces. In Proc. ECCV, 2010. 2
14. T. Hofmann. Probabilistic latent semantic indexing. In SIGIR, 1999. 2
15. N. Ikizler-Cinbis, R. G. Cinbis, and S. Sclaroff. Learning actions from the web. In Proc. ICCV, 2009. 1, 2
16. A. Karmaker and S. Kwek. A boosting approach to remove class label noise. In Proc. International Conference on Hybrid Intelligent Systems, pages 206-211, 2005. 2, 6
17. J. D. Keeler, D. E. Rumelhart, and W.-K. Leow. Integrated segmentation and recognition of hand-printed numerals. In NIPS, 1990. 8
18. T. Leung and J. Malik. Representing and recognizing the visual appearance of materials using three-dimensional textons. IJCV, 43(1), 2001. 4
19. L.-J. Li, G.Wang, and L. Fei-Fei. Optimol: Automatic object picture collection via incremental model learning. In Proc. CVPR, 2007. 1, 2
20. R. Lyon, M. Rehn, S. Bengio, T. Walters, and G. Chechik. Sound retrieval and ranking using sparse auditory representations. Neural computation, 22(9):2390-2416, 2010. 4
21. R. E. Neapolitan. Learning Bayesian Networks. Prentice-Hall, Inc., 2003. 4
22. J. Shotton, M. Johnson, and R. Cipolla. Semantictexton forests for image categorization and segmentation. In Proc. CVPR, 2008. 4
23. J. Sivic, B. C. Russell, A. Efros, A. Zisserman, and W. T. Freeman. Discovering object categories in image collections. In Proc. ICCV, 2005. 2
24. Y. Song, M. Zhao, J. Yagnik, and X. Wu. Taxonomic classification for web-based videos. In CVPR, 2010. 2, 3, 4
25. A. Vezhnevets and J. Buhmann. Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning. In Proc. CVPR, 2010. 2
26. S. Vijayanarasimhan and K. Grauman. Keywords to visual categories: Multiple-instance learning for weakly supervised object categorization. In Proc. CVPR, 2008. 2
27. P.Viola andM. Jones. Rapid object detection using a boosted cascade of simple features. Proc. CVPR, 2001. 4
28. P. Viola, J. C. Platt, and C. Zhang. Multiple instance boosting for object detection. In NIPS, 2006. 1, 2, 3
29. Z.Wang, et. al. Youtubecat: Learning to categorize wild web videos. CVPR, 2010. 1
30. S. Zanetti, L. Zelnik-Manor, and P. Perona. A walk through the web's video clips. In Proc. 1st IEEE Workshop on Internet Vision, 2008. 1, 2
31. X. Zhu, X.Wu, and Q. Chen. Eliminating class noise in large datasets. In Proc. ICML, 2003. 2