TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/VideoChat-T (7B)

VideoChat-T (7B)

Reported on 9 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.

Reasoning5 results

  • Video Question AnsweringonMVBench
    Avg.· 2024-10-25
    59.9
    best: 69.3 (LinVT-Qwen2-VL (7B))
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702
  • Video Question AnsweringonVideo-MME (w/o subs)
    Accuracy (%)· 2024-10-25
    46.3
    best: 77.4 (Video-RAG (based on LLaVA-Video))
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702
  • Video Question AnsweringonVideo-MME
    Accuracy (%)· 2024-10-25
    55.8
    best: 81.3 (Gemini 1.5 Pro)
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702
  • Video Question AnsweringonEgoSchema (fullset)
    Accuracy· 2024-10-25
    60
    best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702
  • Video Question AnsweringonEgoSchema (subset)
    Accuracy· 2024-10-25
    68.4
    best: 68.6 (Tarsier (34B))
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702

Natural Language Processing4 results

  • Question AnsweringonVideo-MME (w/o subs)
    Accuracy (%)· 2024-10-25
    46.3
    best: 77.4 (Video-RAG (based on LLaVA-Video))
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702
  • Question AnsweringonVideo-MME
    Accuracy (%)· 2024-10-25
    55.8
    best: 81.3 (Gemini 1.5 Pro)
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702
  • Question AnsweringonEgoSchema (fullset)
    Accuracy· 2024-10-25
    60
    best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702
  • Question AnsweringonEgoSchema (subset)
    Accuracy· 2024-10-25
    68.4
    best: 68.6 (Tarsier (34B))
    TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningarXiv:2410.19702