Long Tail Video Object Segmentation On Burst 1
평가 지표
HOTA (all)
HOTA (com)
HOTA (unc)
mAP (all)
mAP (com)
mAP (unc)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | HOTA (all) | HOTA (com) | HOTA (unc) | mAP (all) | mAP (com) | mAP (unc) | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| GLEE-Lite | 22.6 | 36.4 | 19.1 | 12.6 | 18.9 | 11.0 | General Object Foundation Model for Images and Videos at Scale | |
| GLEE-Pro | 31.2 | 48.7 | 26.9 | 19.2 | 24.8 | 17.7 | General Object Foundation Model for Images and Videos at Scale | |
| Box Tracker | 8.2 | 27.0 | 3.6 | 1.4 | 3.0 | 0.9 | BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video | |
| STCN Tracker | 5.5 | 17.5 | 2.5 | 0.9 | 0.7 | 0.6 | BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video | |
| GLEE-Plus | 26.9 | 38.8 | 23.9 | 17.2 | 23.7 | 15.5 | General Object Foundation Model for Images and Videos at Scale |
0 of 5 row(s) selected.