Human action recognition by learning bases of action attributes and parts

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 th...

Full description

Saved in:
Bibliographic Details
Main Authors: Bangpeng Yao, Xiaoye Jiang, Khosla, A., Lin, A. L., Guibas, L., Li Fei-Fei
Format: Conference Proceeding
Language:English
Subjects:
Detectors
Feature extraction
Humans
Image recognition
Image reconstruction
Noise
Vectors
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1550-5499
2380-7504
DOI:10.1109/ICCV.2011.6126386