ReVisionLLM

Reported on 5 benchmarks across 3 tasks · 1 paper · 5 SOTA

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

Computer Vision5 results

VideoonMAD
R@1,IoU=0.1· 2024-11-22
17.3
SOTA
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos arXiv:2411.14901
VideoonMAD
R@1,IoU=0.3· 2024-11-22
12.7
SOTA
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos arXiv:2411.14901
VideoonMAD
R@1,IoU=0.5· 2024-11-22
6.7
best: 7.06 (DeCafNet)
SOTA
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos arXiv:2411.14901
Temporal LocalizationonVidChapters-7M
R1@.9· 2024-11-22
15.2
SOTA
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos arXiv:2411.14901
Language-Based Temporal LocalizationonVidChapters-7M
R1@.9· 2024-11-22
15.2
SOTA
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos arXiv:2411.14901