ABSTRACT
In this paper, we focus on interaction prediction which infers to what interaction might happen in the near future. Each interaction is modeled by mixtures of deformable parts in order to provide higher tolerance to part configurations. In our weakly supervised learning setting, part detectors are learned from training data without bounding boxes around the true locations of the people in each frame. The discriminating features are obtained using a two-layer Linear Discriminant Analysis (LDA) classification to promise maximal separability for parts and interactions respectively. Experimental results demonstrate that the proposed system is effective in learning part-based models in less annotated information and achieves comparable performance to state-of-the-art fully supervised approaches.
- M. Ryoo, "Human activity prediction: Early recognition of ongoing activities from streaming videos," in Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011, pp. 1036--1043. Google ScholarDigital Library
- M. Raptis and L. Sigal, "Poselet key-framing: A model for human activity recognition," in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. IEEE, 2013, pp. 2650--2657. Google ScholarDigital Library
- T. Lan, T.-C. Chen, and S. Savarese, "A hierarchical representation for future action prediction," in Computer Vision--ECCV 2014. Springer, 2014, pp. 689--704.Google Scholar
- I. Endres, K. Shih, J. Jiaa, and D. Hoiem, "Learning collections of part models for object recognition," in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. IEEE, 2013, pp. 939--946. Google ScholarDigital Library
- M. Juneja, A. Vedaldi, C. Jawahar, and A. Zisserman, "Blocks that shout: Distinctive parts for scene classification," in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. IEEE, 2013, pp. 923--930. Google ScholarDigital Library
- C. Doersch, A. Gupta, and A. A. Efros, "Mid-level visual element discovery as discriminative mode seeking," in Advances in Neural Information Processing Systems, 2013, pp. 494--502.Google Scholar
- Y. Yang and D. Ramanan, "Articulated pose estimation with flexible mixtures-of-parts," in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011, pp. 1385--1392. Google ScholarDigital Library
- B. Hariharan, J. Malik, and D. Ramanan, "Discriminative decorrelation for clustering and classification," in Computer Vision--ECCV 2012. Springer, 2012, pp. 459--472. Google ScholarDigital Library
- N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1. IEEE, 2005, pp. 886--893. Google ScholarDigital Library
- H. Wang and C. Schmid, "Action recognition with improved trajectories," in Computer Vision (ICCV), 2013 IEEE International Conference on. IEEE, 2013, pp. 3551--3558. Google ScholarDigital Library
- M. S. Ryoo and J. K. Aggarwal, "UT-Interaction Dataset, ICPR contest on Semantic Description of Human Activities (SDHA)," http://cvrc.ece.utexas.edu/SDHA2010/Human_Interaction.html, 2010.Google Scholar
Index Terms
- Weakly Supervised Learning of Part-based Models for Interaction Prediction via LDA
Recommendations
Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification
WWW '19: The World Wide Web ConferenceHierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to reduce the ...
Semantic Segmentation based on Stacked Discriminative Autoencoders and Context-Constrained Weakly Supervised Learning
MM '15: Proceedings of the 23rd ACM international conference on MultimediaIn this paper, we focus on tacking the problem of weakly supervised semantic segmentation. The aim is to predict the class label of image regions under weakly supervised settings, where training images are only provided with image-level labels ...
Weakly supervised label distribution learning based on transductive matrix completion with sample correlations
Highlights- The matrix completion is firstly applied to weakly supervised LDL problems.
- ...
AbstractLabel distribution learning (LDL) is one of the paradigms for dealing with label ambiguity, and it can learn the relative importance of each label to a particular instance. Most of the existing LDL approaches require strong supervision ...
Comments