Papers › Dual Prototype Attention for Unsupervised Video Object Segmentation
Dual Prototype Attention for Unsupervised Video Object Segmentation
Suhwan Cho, Minhyeok Lee, Seunghoon Lee, Dogyoon Lee, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee
Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos. The primary techniques used in unsupervised VOS are 1) the collaboration of appearance and motion information; and 2) temporal fusion between different frames. This paper proposes two novel prototype-based attention mechanisms, inter-modality attention (IMA) and inter-frame attention (IFA), to incorporate these techniques via dense propagation across different modalities and frames. IMA densely integrates context information from different modalities based on a mutual refinement. IFA injects global context of a video to the query frame, enabling a full utilization of useful properties from multiple frames. Experimental results on public benchmark datasets demonstrate that our proposed approach outperforms all existing methods by a substantial margin. The proposed two components are also thoroughly validated via ablative study.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Unsupervised Video Object Segmentation | DAVIS 2016 val | DPA | F | 88.4 | #4 of 25 | Archive leaderboard | report |
| Unsupervised Video Object Segmentation | DAVIS 2016 val | DPA | G | 87.6 | #4 of 25 | Archive leaderboard | report |
| Unsupervised Video Object Segmentation | DAVIS 2016 val | DPA | J | 86.8 | #4 of 25 | Archive leaderboard | report |
| Unsupervised Video Object Segmentation | FBMS test | DPA | J | 83.4 | #2 of 15 | Archive leaderboard | report |
| Unsupervised Video Object Segmentation | YouTube-Objects | DPA | J | 73.7 | #3 of 16 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections