Video Object Segmentation with Re-identification
arXiv: Computer Vision and Pattern Recognition, Volume abs/1708.00197, 2017.
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. Specifical...More
Full Text (Upload PDF)
PPT (Upload PPT)