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/LaT

LaT

Reported on 24 benchmarks across 1 task · 1 paper · 12 SOTA

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

Computer Vision24 results

  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text Median Rank· 2022-07-11
    12
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text R@1· 2022-07-11
    17.2
    best: 53.7 (InternVideo2-6B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text R@10· 2022-07-11
    47.9
    best: 84.1 (InternVideo2-6B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSR-VTT
    video-to-text R@5· 2022-07-11
    36.2
    best: 77.5 (InternVideo2-6B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    video-to-text Median Rank· 2022-07-11
    3
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    video-to-text R@1· 2022-07-11
    34.4
    best: 83.3 (InternVideo2-1B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    video-to-text R@10· 2022-07-11
    79.2
    best: 97.9 (LanguageBind(ViT-L/14))
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    video-to-text R@5· 2022-07-11
    69
    best: 94.3 (InternVideo2-1B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    video-to-text Median Rank· 2022-07-11
    7
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    video-to-text R@1· 2022-07-11
    22.5
    best: 57.1 (InternVideo2-6B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    video-to-text R@10· 2022-07-11
    56.8
    best: 85 (InternVideo2-6B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    video-to-text R@5· 2022-07-11
    45.2
    best: 79.9 (InternVideo2-6B)
    SOTA
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video Median Rank· 2022-07-11
    8
    best: 66 (MMT)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@1· 2022-07-11
    23.4
    best: 55.9 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@10· 2022-07-11
    53.3
    best: 85.1 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@5· 2022-07-11
    44.1
    best: 78.3 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    text-to-video Median Rank· 2022-07-11
    2
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    text-to-video R@1· 2022-07-11
    36.9
    best: 59.3 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    text-to-video R@10· 2022-07-11
    81
    best: 89.6 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonMSVD
    text-to-video R@5· 2022-07-11
    68.6
    best: 84.4 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video Median Rank· 2022-07-11
    7
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@1· 2022-07-11
    22.6
    best: 57.9 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@10· 2022-07-11
    58.9
    best: 85.1 (InternVideo2-1B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@5· 2022-07-11
    45.9
    best: 80 (InternVideo2-6B)
    LaT: Latent Translation with Cycle-Consistency for Video-Text RetrievalarXiv:2207.04858