Human action recognition by learning bases of action attributes and parts

  • Authors:

  • Bangpeng Yao;Xiaoye Jiang;Aditya Khosla;Andy Lai Lin;Leonidas Guibas;Li Fei-Fei

  • Affiliations:

  • Computer Science Department, Stanford University, CA, USA;Institute for Computational & Mathematical Engineering, Stanford University, CA, USA;Computer Science Department, Stanford University, CA, USA;Electrical Engineering Department, Stanford University, CA, USA;Computer Science Department, Stanford University, CA, USA;Computer Science Department, Stanford University, CA, USA

  • Venue:
  • ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

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.