Name
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. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/CVPR.2015.7298625 | 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
Keywords | Field | DocType |
camera wearer action recognition,egocentric camera,egocentric videos,head movement,hand pose,gaze information,mid-level egocentric cues,egocentric action recognition,motion feature,object feature | Computer vision,ENCODE,Gaze,Computer science,Action recognition,Artificial intelligence | Conference |
Volume | Issue | ISSN |
2015 | 1 | 1063-6919 |
Citations | PageRank | References |
46 | 1.03 | 33 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yin Li | 1 | 797 | 35.85 |
| Zhefan Ye | 2 | 101 | 4.79 |
| James M. Rehg | 3 | 5259 | 474.66 |