Semi-Supervised Video Object Segmentation
The semi-supervised scenario assumes the user inputs a full mask of the object(s) of interest in the first frame of a video sequence. Methods have to produce the segmentation mask for that object(s) in the subsequent frames.
Papers
Showing 1–10 of 147 papers
All datasetsDAVIS 2017 (val)DAVIS 2016DAVIS-2017 (test-dev)YouTube-VOS 2018DAVIS (no YouTube-VOS training)YouTube-VOS 2019VOT2020MOSELong Video DatasetYouTubeDAVIS 2017BURST-test
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SAM2 | J&F | 77.9 | — | Unverified |
| 2 | Cutie+ (base, MEGA) | J&F | 71.7 | — | Unverified |
| 3 | Cutie+ (small, MEGA) | J&F | 70.3 | — | Unverified |
| 4 | Cutie (base, MEGA) | J&F | 69.9 | — | Unverified |
| 5 | Cutie (small, MEGA) | J&F | 68.6 | — | Unverified |
| 6 | Cutie (base, with mose) | J&F | 68.3 | — | Unverified |
| 7 | Cutie (small, with mose) | J&F | 67.4 | — | Unverified |
| 8 | DEVA (with OVIS) | J&F | 66.5 | — | Unverified |
| 9 | Cutie (base) | J&F | 64 | — | Unverified |
| 10 | Cutie (small) | J&F | 62.2 | — | Unverified |