Multi-scale region candidate combination for action recognition
Lists
Only you see this
Abstract
In still images, multi-scale regions contain rich information of different granularity. However, only semantically meaningful regions provide auxiliary cues for action recognition. Moreover, regions at different scales contribute differently. Motivated by the two observations, we propose an approach that is composed of three components: 1) detecting semantic region candidates at multiple scales, 2) training networks at each scale, 3) extracting features and learning to fuse them. The proposed approach captures multi-scale cues and highlights the optimal scale for each action, Experimental results show that our approach reaches the state-of-the-art performance on two challenging benchmarks: 1) PASCAL VOC 2012 and 2) Stanford-40.
BibTeX
@inproceedings{zhao2016multi,
author = {Zhichen Zhao and Huimin Ma and Xiaozhi Chen},
title = {{Multi-scale region candidate combination for action recognition}},
booktitle = {ICIP},
year = {2016},
url = {https://openreview.net/forum?id=KX1ODAA9ThG},
}Loading related content...