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/Cap4Video

Cap4Video

Reported on 74 benchmarks across 2 tasks · 1 paper · 12 SOTA

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

Computer Vision74 results

  • VideoonVATEX
    text-to-video MeanR· 2022-12-31
    2.7
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonVATEX
    text-to-video MedianR· 2022-12-31
    1
    best: 2.7 (Side4Video)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonVATEX
    text-to-video R@10· 2022-12-31
    97
    best: 100 (GRAM)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonVATEX
    text-to-video R@5· 2022-12-31
    93.1
    best: 98.2 (VAST)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonVATEX
    video-to-text R@10· 2022-12-31
    99.6
    best: 100 (GRAM)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    video-to-text R@10· 2022-12-31
    87.4
    best: 93.8 (vid-TLDR (UMT-L))
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonVATEX
    text-to-video MeanR· 2022-12-31
    2.7
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonVATEX
    text-to-video MedianR· 2022-12-31
    1
    best: 2.7 (Side4Video)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonVATEX
    text-to-video R@10· 2022-12-31
    97
    best: 100 (GRAM)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonVATEX
    text-to-video R@5· 2022-12-31
    93.1
    best: 98.2 (VAST)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonVATEX
    video-to-text R@10· 2022-12-31
    99.6
    best: 100 (GRAM)
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    video-to-text R@10· 2022-12-31
    87.4
    best: 93.8 (vid-TLDR (UMT-L))
    SOTA
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    text-to-video Mean Rank· 2022-12-31
    12.4
    best: 28.2 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· 2022-12-31
    1
    best: 13 (JSFusion)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    text-to-video R@1· 2022-12-31
    51.4
    best: 62.9 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    text-to-video R@10· 2022-12-31
    83.9
    best: 90.8 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    text-to-video R@5· 2022-12-31
    75.7
    best: 84.5 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    video-to-text Mean Rank· 2022-12-31
    8
    best: 10.2 (CenterCLIP (ViT-B/16))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    video-to-text Median Rank· 2022-12-31
    2
    best: 5 (CLIP)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    video-to-text R@1· 2022-12-31
    49
    best: 64.8 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    video-to-text R@10· 2022-12-31
    85
    best: 91.1 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSR-VTT-1kA
    video-to-text R@5· 2022-12-31
    75.2
    best: 783 (PIDRo)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonVATEX
    text-to-video R@1· 2022-12-31
    66.6
    best: 87.7 (GRAM)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonVATEX
    video-to-text R@1· 2022-12-31
    80.9
    best: 89.3 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    text-to-video Mean Rank· 2022-12-31
    10.5
    best: 43.7 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    text-to-video Median Rank· 2022-12-31
    1
    best: 8.3 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    text-to-video R@1· 2022-12-31
    52
    best: 74.2 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    text-to-video R@10· 2022-12-31
    87.5
    best: 94.2 (vid-TLDR (UMT-L))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    text-to-video R@5· 2022-12-31
    79.4
    best: 91.2 (vid-TLDR (UMT-L))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    video-to-text Mean Rank· 2022-12-31
    7.3
    best: 39.6 (PO Loss)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    video-to-text Median Rank· 2022-12-31
    1
    best: 8 (PO Loss)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    video-to-text R@1· 2022-12-31
    51.2
    best: 71.9 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonDiDeMo
    video-to-text R@5· 2022-12-31
    78.5
    best: 89.8 (vid-TLDR (UMT-L))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    text-to-video Mean Rank· 2022-12-31
    8.3
    best: 23.1 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    text-to-video Median Rank· 2022-12-31
    1
    best: 6 (SSML)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    text-to-video R@1· 2022-12-31
    51.8
    best: 61.4 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    text-to-video R@10· 2022-12-31
    88.3
    best: 90.3 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    text-to-video R@5· 2022-12-31
    80.8
    best: 87.6 (CAMoE)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    video-to-text Mean Rank· 2022-12-31
    2.4
    best: 7.6 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    video-to-text Median Rank· 2022-12-31
    1
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    video-to-text R@1· 2022-12-31
    70
    best: 85.2 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    video-to-text R@10· 2022-12-31
    96.2
    best: 97.1 (PAU)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • VideoonMSVD
    video-to-text R@5· 2022-12-31
    93.2
    best: 94.5 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Mean Rank· 2022-12-31
    12.4
    best: 28.2 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· 2022-12-31
    1
    best: 13 (JSFusion)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· 2022-12-31
    51.4
    best: 62.9 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· 2022-12-31
    83.9
    best: 90.8 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· 2022-12-31
    75.7
    best: 84.5 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Mean Rank· 2022-12-31
    8
    best: 10.2 (CenterCLIP (ViT-B/16))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Median Rank· 2022-12-31
    2
    best: 5 (CLIP)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@1· 2022-12-31
    49
    best: 64.8 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@10· 2022-12-31
    85
    best: 91.1 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@5· 2022-12-31
    75.2
    best: 783 (PIDRo)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonVATEX
    text-to-video R@1· 2022-12-31
    66.6
    best: 87.7 (GRAM)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonVATEX
    video-to-text R@1· 2022-12-31
    80.9
    best: 89.3 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    text-to-video Mean Rank· 2022-12-31
    10.5
    best: 43.7 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    text-to-video Median Rank· 2022-12-31
    1
    best: 8.3 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    text-to-video R@1· 2022-12-31
    52
    best: 74.2 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    text-to-video R@10· 2022-12-31
    87.5
    best: 94.2 (vid-TLDR (UMT-L))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    text-to-video R@5· 2022-12-31
    79.4
    best: 91.2 (vid-TLDR (UMT-L))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    video-to-text Mean Rank· 2022-12-31
    7.3
    best: 39.6 (PO Loss)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    video-to-text Median Rank· 2022-12-31
    1
    best: 8 (PO Loss)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    video-to-text R@1· 2022-12-31
    51.2
    best: 71.9 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonDiDeMo
    video-to-text R@5· 2022-12-31
    78.5
    best: 89.8 (vid-TLDR (UMT-L))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    text-to-video Mean Rank· 2022-12-31
    8.3
    best: 23.1 (Collaborative Experts)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    text-to-video Median Rank· 2022-12-31
    1
    best: 6 (SSML)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    text-to-video R@1· 2022-12-31
    51.8
    best: 61.4 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    text-to-video R@10· 2022-12-31
    88.3
    best: 90.3 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    text-to-video R@5· 2022-12-31
    80.8
    best: 87.6 (CAMoE)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    video-to-text Mean Rank· 2022-12-31
    2.4
    best: 7.6 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    video-to-text Median Rank· 2022-12-31
    1
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    video-to-text R@1· 2022-12-31
    70
    best: 85.2 (InternVideo2-6B)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    video-to-text R@10· 2022-12-31
    96.2
    best: 97.1 (PAU)
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184
  • Video RetrievalonMSVD
    video-to-text R@5· 2022-12-31
    93.2
    best: 94.5 (HunYuan_tvr (huge))
    Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?arXiv:2301.00184