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/RTQ

RTQ

Reported on 25 benchmarks across 4 tasks · 1 paper

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

Computer Vision24 results

  • VideoonMSR-VTT-1kA
    text-to-video R@1· 2023-12-01
    53.4
    best: 62.9 (HunYuan_tvr (huge))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonMSR-VTT-1kA
    text-to-video R@10· 2023-12-01
    84.4
    best: 90.8 (HunYuan_tvr (huge))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonMSR-VTT-1kA
    text-to-video R@5· 2023-12-01
    76.1
    best: 84.5 (HunYuan_tvr (huge))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonActivityNet
    text-to-video R@1· 2023-12-01
    53.5
    best: 74.1 (InternVideo2-6B)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonActivityNet
    text-to-video R@10· 2023-12-01
    91.9
    best: 96.1 (GRAM)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonActivityNet
    text-to-video R@5· 2023-12-01
    81.4
    best: 90.9 (VAST)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonDiDeMo
    text-to-video R@1· 2023-12-01
    57.6
    best: 74.2 (InternVideo2-6B)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonDiDeMo
    text-to-video R@10· 2023-12-01
    89.9
    best: 94.2 (vid-TLDR (UMT-L))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • VideoonDiDeMo
    text-to-video R@5· 2023-12-01
    84.1
    best: 91.2 (vid-TLDR (UMT-L))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video CaptioningonMSR-VTT
    BLEU-4· uses extra data· 2023-12-01
    49.6
    best: 57.8 (mPLUG-2)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video CaptioningonMSR-VTT
    CIDEr· uses extra data· 2023-12-01
    69.3
    best: 80 (mPLUG-2)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video CaptioningonMSR-VTT
    ROUGE-L· uses extra data· 2023-12-01
    66.1
    best: 70.1 (mPLUG-2)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video CaptioningonMSVD
    BLEU-4· 2023-12-01
    66.9
    best: 80.7 (VALOR)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video CaptioningonMSVD
    CIDEr· 2023-12-01
    123.4
    best: 195.6 (MaMMUT)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video CaptioningonMSVD
    ROUGE-L· 2023-12-01
    82.2
    best: 87.9 (VLAB)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· 2023-12-01
    53.4
    best: 62.9 (HunYuan_tvr (huge))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· 2023-12-01
    84.4
    best: 90.8 (HunYuan_tvr (huge))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· 2023-12-01
    76.1
    best: 84.5 (HunYuan_tvr (huge))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonActivityNet
    text-to-video R@1· 2023-12-01
    53.5
    best: 74.1 (InternVideo2-6B)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonActivityNet
    text-to-video R@10· 2023-12-01
    91.9
    best: 96.1 (GRAM)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonActivityNet
    text-to-video R@5· 2023-12-01
    81.4
    best: 90.9 (VAST)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonDiDeMo
    text-to-video R@1· 2023-12-01
    57.6
    best: 74.2 (InternVideo2-6B)
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonDiDeMo
    text-to-video R@10· 2023-12-01
    89.9
    best: 94.2 (vid-TLDR (UMT-L))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347
  • Video RetrievalonDiDeMo
    text-to-video R@5· 2023-12-01
    84.1
    best: 91.2 (vid-TLDR (UMT-L))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347

Reasoning1 result

  • Video Question AnsweringonNExT-QA
    Accuracy· 2023-12-01
    63.2
    best: 85.5 (LinVT-Qwen2-VL (7B))
    RTQ: Rethinking Video-language Understanding Based on Image-text ModelarXiv:2312.00347