Search Results for author:
Found 2 papers, 0 papers with code
Space-time Reinforcement Network for Video Object Segmentation
Recently, video object segmentation (VOS) networks typically use memory-based methods: for each query frame, the mask is predicted by space-time matching to memory frames.
Robust and Efficient Memory Network for Video Object Segmentation
For limitation 2, we first adaptively decide whether to update the memory features depending on the variation of foreground objects to reduce temporal redundancy.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
