GVL (paragraph-level)

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Computer Vision4 results

VideoonTACoS
R@1,IoU=0.3· 2023-03-11
48.29
best: 58.1 (SG-DETR (w/ PT))
SOTA
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos arXiv:2303.06378
VideoonTACoS
R@1,IoU=0.5· 2023-03-11
36.07
best: 46.79 (DeCafNet)
SOTA
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos arXiv:2303.06378
VideoonActivityNet Captions
R@1,IoU=0.5· 2023-03-11
60.67
SOTA
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos arXiv:2303.06378
VideoonActivityNet Captions
R@1,IoU=0.7· 2023-03-11
38.55
SOTA
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos arXiv:2303.06378