Work

Delving into egocentric actions

Year: 2015

Type: conference-paper

Abstract: We address the challenging problem of recognizing the camera wearer's actions from videos captured by an egocentric camera. Egocentric videos encode a rich set of signals regarding the camera wearer, including head movement, hand pose and gaze information. We propose to utilize these mid-level egocentric cues for egocentric action recognition. We present a novel set of egocentric features and show how they can be combined with motion and object features. The result is a compact representation with superior performance. In addition, we provide the first systematic evaluation of motion, object and egocentric cues in egocentric action recognition. Our benchmark leads to several surprising findings. These findings uncover the best practices for egocentric actions, with a significant performance boost over all previous state-of-the-art methods on three publicly available datasets.

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr.2015.7298625

Authors: Yin Li, Zhefan Ye, James M. Rehg

Institution: Georgia Institute of Technology

Language: English

Topic: Human Pose and Action Recognition

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: International Science and Technology Center, National Institute of Biomedical Imaging and Bioengineering

Award: Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) - OVERALL