Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas Guibas, and Fei-Fei Li. Human Action Recognition by Learning Bases of Action Attributes and Parts. The Thirteenth International Conference on Computer Vision (ICCV). Barcelona, Spain, November 2011.

Abstract:

In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of human actions, while the parts of actions are objects and poselets that are closely related to the actions. We jointly model the attributes and parts by learning a set of sparse bases that are shown to carry much semantic meaning. Then, the attributes and parts of an action image can be reconstructed from sparse coefficients with respect to the learned bases. This dual sparsity provides theoretical guarantee of our bases learning and feature reconstruction approach. On the PASCAL action dataset and a new “Stanford 40 Actions” dataset, we show that our method extracts meaningful high-order interactions between attributes and parts in human actions while achieving state-of-the-art classification performance.

Bibtex: 

@inproceedings{yjklgl-harlbaap-11,
author = {Bangpeng Yao and Xiaoye Jiang and Aditya Khosla and Andy~Lai Lin and Leonidas Guibas and Li Fei-Fei},
title = {Action Recognition by Learning Bases of Action Attributes and Parts},
booktitle = {In Proceedings of the 13th International Conference on Computer Vision (ICCV)},
year = {2011}
}