794 citations · 1.6k across the 27 of their papers we have counts for
Showing 2017 · cs.CVShow all
2 papers · 2 filters
cs.CV2017★ 67 cited
Video Object Segmentation with Re-identification
Xiaoxiao Li, Yuankai Qi, Zhe Wang +6
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 dis…
cs.CV2017★ 4 cited
Discover and Learn New Objects from Documentaries
Kai Chen, Hang Song, Chen Change Loy +1
Despite the remarkable progress in recent years, detecting objects in a new context remains a challenging task. Detectors learned from a public dataset can only work with a fixed l…