Video Object Segmentation with Re-identification

Xiaoxiao Li    Yuankai Qi    Zhe Wang    Kai Chen    Ziwei Liu    Jianping Shi    Ping Luo    Xiaoou Tang    Chen Change Loy
Multimedia Laboratory, The Chinese University of Hong Kong
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, DAVIS Video Seg. Challenge, Winning Entry

Abstract


Conventional video segmentation methods often rely on temporal continuity to propagate masks. Such an assumption suffers from issues like drifting and inability to handle large displacement. To overcome these issues, we formulate an effective mechanism to prevent the target from being lost via adaptive object re-identification. Specifically, our Video Object Segmentation with Re-identification (VS- ReID) model includes a mask propagation module and a ReID module. The former module produces an initial probability map by flow warping while the latter module retrieves missing instances by adaptive matching. With these two modules iteratively applied, our VS-ReID records a global mean (Region Jaccard and Boundary F measure) of 0.699, the best performance in 2017 DAVIS Challenge.

Demo



Materials


Code and Models


Citation

@inproceedings{zhan2018m&m,
 author = {Xiaoxiao Li, Yuankai Qi, Zhe Wang, Kai Chen, Ziwei Liu, Jianping Shi, Ping Luo, Xiaoou Tang, and Chen Change Loy},
 title = {Video Object Segmentation with Re-identification},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop},
 month = {July},
 year = {2017} 
}