SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation
Video Object Segmentation (VOS) aims to accurately segment target objects from consecutive video frames and track the changes of the objects in each frame of the video. Conventional VOS methods typically demand substantial quantities of pixel-level labeled video sequences for fully supervised learning, which limits the...
Zheng Zhu, Jia-Qing Fan, Han-Wen Qian et al.
· 0 citations