Partwise bag-of-words-based multi-task learning for human action recognition
暂无分享,去创建一个
Proposed is a human action recognition method by partwise bag-of-words (BoW)-based multi-task learning. The authors present partwise BoW representation and furthermore formulate the action recognition task as a joint multi-task learning problem by transfer learning penalised by a graph structure and sparsity to discover latent correlation and boost performances. A large-scale experiment shows that this method can significantly improve performance over the standard BoW + SVM method. Moreover, the proposed method can achieve competing performances against the state-of-the-art methods for human action recognition in an effective and easy to follow way.
[1] Quoc V. Le,et al. Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis , 2011, CVPR 2011.
[2] Cordelia Schmid,et al. Evaluation of Local Spatio-temporal Features for Action Recognition , 2009, BMVC.
[3] David A. McAllester,et al. Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.
[4] An-An Liu,et al. Human action recognition with structured discriminative random fields , 2011 .