LocVLM-Vid-B

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

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

Reasoning4 results

Video Question AnsweringonMSR-VTT
Accuracy· 2024-04-11
51.2
SOTA
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Video Question AnsweringonActivityNet-QA
Accuracy· 2024-04-11
37.4
best: 61.6 (Tarsier (34B))
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Video Question AnsweringonMSVD-QA
Accuracy· 2024-04-11
66.1
best: 80.3 (Tarsier (34B))
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449
Video Question AnsweringonTGIF-QA
Accuracy· 2024-04-11
51.8
best: 82.5 (Tarsier (34B))
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs arXiv:2404.07449