Abstract
In this chapter we study the problem of classifying human–object interaction activities in still images. The goal of our method is to explore fine image statistics and identify the discriminative image patches for recognition. We achieve this goal by combining two ideas, discriminative feature mining and randomization. Discriminative feature mining allows us to model the detailed information that distinguishes different classes of images, while randomization allows us to handle the huge feature space and prevent over-fitting. We propose a random forest with discriminative decision trees algorithm where every tree node is a discriminative classifier that is trained by combining the information in this node as well as all upstream nodes. Besides human action recognition in still images, we also evaluate our method on subordinate categorization. Experimental results show that our method identifies semantically meaningful visual information and outperforms state-of-the-art algorithms on various datasets. Using our method, we achieved the best results and won the award in PASCAL VOC action classification challenges in 2011 and 2012.
An early version of this chapter was presented in Yao et al. [37], and the code is available at http://vision.stanford.edu/discrim_rf/
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We use the terms “patches” and “regions” interchangeably throughout this chapter.
- 2.
- 3.
The baseline results are available from the dataset website: http://ai.stanford.edu/~bangpeng/ppmi
- 4.
A summary of the results in 2011 PASCAL challenge is in http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2011/workshop/index.html http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2011/workshop/index.html.
- 5.
A summary of the results in 2012 PASCAL challenge is in http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/workshop/index.html http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/workshop/index.html.
- 6.
These approaches were specifically developed for the 2012 PASCAL VOC challenge and have not been tested on other datasets but we expect similar performance improvements on them.
References
Bernard, S., Heutte, L., Adam, S.: On the selection of decision trees in random forests. In: IEEE International Joint Conference on Neural Networks, IJCNN, pp. 302–307 (2009)
Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2007)
Branson, S., Wah, C., Babenko, B., Schroff, F., Welinder, P., Perona, P., Belongie, S.: Visual recognition with humans in the loop. In: Proceedings of the European Conference on Computer Vision (ECCV) (2010)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Collin, C.A., McMullen, P.A.: Subordinate-level categorization relies on high spatial frequencies to a greater degree than basic-level categorization. Percept. Psychophys. 67(2), 354–364 (2005)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)
Delaitre, V., Laptev, I., Sivic, J.: Recognizing human actions in still images: a study of bag-of-features and part-based representations. In: Proceedings of the British Machine Vision Conference (BMVC) (2010)
Dietterich, T.G.: An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach. Learn. 40, 139–157 (2000)
Duan, G., Huang, C., Ai, H., Lao, S.: Boosting associated pairing comparison features for pedestrian detection. In: Proceedings of the Workshop on Visual Surveillance (2009)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2010 (VOC2010) Results (2010)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2011 (VOC2011) Results (2011)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2011 (VOC2012) Results (2012)
Fei-Fei, L., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)
Fei-Fei, L., Fergus, R., Torralba, A.: Recognizing and learning object categories. Short Course in the IEEE International Conference on Computer Vision (2009)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminantly trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627–1645 (2010)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2003)
Hillel, A.B., Weinshall, D.: Subordinate class recognition using relational object models. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS) (2007)
Johnson, K.E., Eilers, A.T.: Effects of knowledge and development on subordinate level categorization. Cogn. Dev. 13(4), 515–545 (1998)
Khosla, A., Xiao, J., Torralba, A., Oliva, A.: Memorability of image regions. In: Advances in Neural Information Processing Systems (NIPS), Lake Tahoe (2012)
Khosla, A., Yao, B., Jayadevaprakash, N., Fei-Fei, L.: Novel dataset for fine-grained image categorization. In: First Workshop on Fine-Grained Visual Categorization, IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs (2011)
Lazebnik, S.: Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2006)
Li, L.-J., Su, H., Xing, E., Fei-Fei, L.: Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS) (2010)
Lowe, David G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)
Moosmann, F., Triggs, B., Jurie, F.: Fast discriminative visual codebooks using randomized clustering forests. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS) (2007)
Ojala, T., Pietikainen, M., Harwood, D.: Performance evaluation of texture measures with classification based on kullback discrimination of distributions. In: Proceedings of the IEEE International Conference on Pattern Recognition (ICPR) (1994)
Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the shape envelope. Int. J. Comput. Vision 42(3), 145–175 (2001)
Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2008)
Tu, Z.: Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2005)
van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Evaluating color descriptors for object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1582–1596 (2010)
van de Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. IEEE Trans. Image Process. 18(7), 1512–1523 (2009)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., Perona, P.: Caltech-UCSD birds 200. Technical Report CNS-TR-201, Caltech (2010)
Yao, B., Fei-Fei, L.: Grouplet: a structured image representation for recognizing human and object interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L. J., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2011)
Yao, B., Khosla, A., Fei-Fei, L.: Classifying actions and measuring action similarity by modeling the mutual context of objects and human poses. In: Proceedings of the International Conference on Machine Learning (ICML) (2011)
Yao, B., Khosla, A., Fei-Fei, L.: Combining randomization and discrimination for fine-grained image categorization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011)
Yao, B., Bradski, G., Fei-Fei, L.: A codebook-free and annotation-free approach for fine-grained image categorization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2012)
Yao, B., Fei-Fei, L.: Action recognition with exemplar based 2.5D graph matching. In: Proceedings of the European Conference on Computer Vision (ECCV) (2012)
Acknowledgments
L.F-F. is partially supported by an NSF CAREER grant (IIS-0845230), an ONR MURI grant, the DARPA VIRAT program and the DARPA Mind’s Eye program. B.Y. is partially supported by the SAP Stanford Graduate Fellowship, and the Microsoft Research Fellowship. A.K. is supported by the Facebook Fellowship.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Khosla, A., Yao, B., Fei-Fei, L. (2014). Integrating Randomization and Discrimination for Classifying Human-Object Interaction Activities. In: Fu, Y. (eds) Human-Centered Social Media Analytics. Springer, Cham. https://doi.org/10.1007/978-3-319-05491-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-05491-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-05490-2
Online ISBN: 978-3-319-05491-9
eBook Packages: Computer ScienceComputer Science (R0)