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/LanguageBind(ViT-H/14)

LanguageBind(ViT-H/14)

Reported on 29 benchmarks across 1 task · 1 paper · 6 SOTA

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

Computer Vision29 results

  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@5· uses extra data· 2023-10-03
    70
    best: 78.3 (InternVideo2-6B)
    SOTA
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text R@1· uses extra data· 2023-10-03
    40.9
    best: 53.7 (InternVideo2-6B)
    SOTA
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text R@5· uses extra data· 2023-10-03
    66.4
    best: 77.5 (InternVideo2-6B)
    SOTA
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonActivityNet
    text-to-video R@10· uses extra data· 2023-10-03
    80
    best: 92.5 (InternVideo2-6B)
    SOTA
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonActivityNet
    video-to-text R@10· uses extra data· 2023-10-03
    81.1
    best: 90.3 (InternVideo2-6B)
    SOTA
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonActivityNet
    video-to-text R@5· uses extra data· 2023-10-03
    69.8
    best: 82.8 (InternVideo2-6B)
    SOTA
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video Median Rank· uses extra data· 2023-10-03
    2
    best: 66 (MMT)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@1· uses extra data· 2023-10-03
    44.8
    best: 55.9 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@10· uses extra data· 2023-10-03
    78.7
    best: 85.1 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text Median Rank· uses extra data· 2023-10-03
    2
    best: 12 (LaT)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text R@10· uses extra data· 2023-10-03
    75.7
    best: 84.1 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    text-to-video Median Rank· uses extra data· 2023-10-03
    1
    best: 2 (HowToCaption)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    text-to-video R@1· uses extra data· 2023-10-03
    53.9
    best: 59.3 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    text-to-video R@10· uses extra data· 2023-10-03
    87.8
    best: 89.6 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    text-to-video R@5· uses extra data· 2023-10-03
    80.4
    best: 84.4 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    video-to-text Median Rank· uses extra data· 2023-10-03
    1
    best: 3 (LaT)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    video-to-text R@1· uses extra data· 2023-10-03
    72
    best: 83.3 (InternVideo2-1B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    video-to-text R@10· uses extra data· 2023-10-03
    96.3
    best: 97.9 (LanguageBind(ViT-L/14))
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonMSVD
    video-to-text R@5· uses extra data· 2023-10-03
    91.4
    best: 94.3 (InternVideo2-1B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video Median Rank· uses extra data· 2023-10-03
    2
    best: 7 (LaT)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@1· uses extra data· 2023-10-03
    39.9
    best: 57.9 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@10· uses extra data· 2023-10-03
    74.6
    best: 85.1 (InternVideo2-1B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@5· uses extra data· 2023-10-03
    66.1
    best: 80 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonDiDeMo
    video-to-text R@1· uses extra data· 2023-10-03
    39.8
    best: 57.1 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonDiDeMo
    video-to-text R@10· uses extra data· 2023-10-03
    76.2
    best: 85 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonDiDeMo
    video-to-text R@5· uses extra data· 2023-10-03
    67.8
    best: 79.9 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonActivityNet
    text-to-video R@1· uses extra data· 2023-10-03
    41
    best: 63.2 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonActivityNet
    text-to-video R@5· uses extra data· 2023-10-03
    68.4
    best: 85.6 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852
  • Zero-Shot Video RetrievalonActivityNet
    video-to-text R@1· uses extra data· 2023-10-03
    39.1
    best: 56.5 (InternVideo2-6B)
    LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentarXiv:2310.01852