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 | HMMN | D17 val (G) | 80.4 | — | Unverified |
| 2 | TBD | D17 val (G) | 80 | — | Unverified |
| 3 | AOT-S | D17 val (G) | 79.2 | — | Unverified |
| 4 | JOINT | D17 val (G) | 78.6 | — | Unverified |
| 5 | SSTVOS | D17 val (G) | 78.4 | — | Unverified |
| 6 | SWEM | D17 val (G) | 77.2 | — | Unverified |
| 7 | KMN | D17 val (G) | 76 | — | Unverified |
| 8 | LCM | D17 val (G) | 75.2 | — | Unverified |
| 9 | RMNet | D17 val (G) | 75 | — | Unverified |
| 10 | CFBI | D17 val (G) | 74.9 | — | Unverified |