VideoLISA

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

VideoonLong-RVOS
J&F· 2024-09-29
33.1
best: 51.3 (ReferMo)
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos arXiv:2409.19603
VideoonLong-RVOS
tIoU· 2024-09-29
69.6
best: 71.7 (ReferDINO)
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos arXiv:2409.19603
VideoonLong-RVOS
vIoU· 2024-09-29
28.2
best: 42.6 (ReferMo)
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos arXiv:2409.19603
Video Object SegmentationonLong-RVOS
J&F· 2024-09-29
33.1
best: 51.3 (ReferMo)
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos arXiv:2409.19603
Video Object SegmentationonLong-RVOS
tIoU· 2024-09-29
69.6
best: 71.7 (ReferDINO)
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos arXiv:2409.19603
Video Object SegmentationonLong-RVOS
vIoU· 2024-09-29
28.2
best: 42.6 (ReferMo)
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos arXiv:2409.19603