Transductive Inference for Text Classification using Support Vector Machines
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition
International Journal of Computer Vision
Transductive support vector machines for structured variables
Proceedings of the 24th international conference on Machine learning
Large margin training for hidden Markov models with partially observed states
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Learning structural SVMs with latent variables
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Object Detection with Discriminatively Trained Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Human activity analysis: A review
ACM Computing Surveys (CSUR)
Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient training for pairwise or higher order CRFs via dual decomposition
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Weakly supervised semantic segmentation with a multi-image model
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Object and Action Classification with Latent Window Parameters
International Journal of Computer Vision
| Hi-index | 0.00 |
We present a novel algorithm for weakly supervised action classification in videos. We assume we are given training videos annotated only with action class labels. We learn a model that can classify unseen test videos, as well as localize a region of interest in the video that captures the discriminative essence of the action class. A novel Similarity Constrained Latent Support Vector Machine model is developed to operationalize this goal. This model specifies that videos should be classified correctly, and that the latent regions of interest chosen should be coherent over videos of an action class. The resulting learning problem is challenging, and we show how dual decomposition can be employed to render it tractable. Experimental results demonstrate the efficacy of the method.