HTR (Pre-training)

Reported on 6 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
F· 2024-03-28
68.9
best: 76.1 (MPG-SAM 2)
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory arXiv:2403.19407
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J· 2024-03-28
65.3
best: 71.7 (MPG-SAM 2)
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory arXiv:2403.19407
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F· 2024-03-28
67.1
best: 73.9 (MPG-SAM 2)
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory arXiv:2403.19407
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
F· 2024-03-28
68.9
best: 76.1 (MPG-SAM 2)
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory arXiv:2403.19407
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J· 2024-03-28
65.3
best: 71.7 (MPG-SAM 2)
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory arXiv:2403.19407
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F· 2024-03-28
67.1
best: 73.9 (MPG-SAM 2)
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory arXiv:2403.19407