Video Object Segmentation
Video object segmentation is a binary labeling problem aiming to separate foreground object(s) from the background region of a video.
For leaderboards please refer to the different subtasks.
Papers
Showing 1–10 of 551 papers
All datasetsDAVIS 2016DAVIS 2017 (val)YouTube-VOS 2018DAVIS-2017 (test-dev)YouTube-VOS 2019DAVIS 2017M^3-VOSFBMSYouTubeFBMS-59MOSESegTrack-v2
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | XMem (BL30K, MS) | Mean Jaccard & F-Measure | 83.7 | — | Unverified |
| 2 | XMem | Mean Jaccard & F-Measure | 81 | — | Unverified |
| 3 | BATMAN | Jaccard | 78.4 | — | Unverified |
| 4 | AOT | Jaccard | 75.9 | — | Unverified |
| 5 | RPCMVOS | Jaccard | 75.8 | — | Unverified |
| 6 | LCM | Jaccard | 74.4 | — | Unverified |
| 7 | KMN | Jaccard | 74.1 | — | Unverified |
| 8 | TransVOS | Jaccard | 73 | — | Unverified |
| 9 | STCN | Jaccard | 72.7 | — | Unverified |
| 10 | RMN | Jaccard | 71.9 | — | Unverified |