TimeChat (7B)

Reported on 3 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.

Reasoning2 results

Video Question AnsweringonOVBench
AVG· 2023-12-04
12.8
best: 60 (Seed1.5-VL)
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding arXiv:2312.02051
Video Question AnsweringonEgoSchema (fullset)
Accuracy· 2023-12-04
33
best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding arXiv:2312.02051

Natural Language Processing1 result

Question AnsweringonEgoSchema (fullset)
Accuracy· 2023-12-04
33
best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding arXiv:2312.02051