Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Video Multimodal Interpretation on LV-VIS (val)
Loading...
26
AP
SG-FSCFormer
23.816
24.383
24.95
25.517
Mar 21, 2026
AP
AP50
AP75
Updated 26d ago
Evaluation Results
Method
Method
Links
AP
AP50
AP75
SG-FSCFormer
Mask Decoder=SAM2
2026.03
26
33.6
28.3
VideoGLaMM
Mask Decoder=SAM2
2026.03
25.4
32.2
27.6
SG-FSCFormer
Mask Decoder=Mask2Former
2026.03
25.2
31.8
27.5
SG-FSCFormer†
Mask Decoder=SAM2, Eva...
2026.03
24.8
31.5
26.9
OVFormer
Mask Decoder=Mask2Former
2026.03
24.7
31.1
26.5
GLEE
Mask Decoder=MaskDINO
2026.03
23.9
24.6
23.3
Feedback
Search any
task
Search any
task