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/UVCOM

UVCOM

Reported on 11 benchmarks across 4 tasks · 1 paper · 3 SOTA

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

Computer Vision10 results

  • VideoonTACoS
    R@1,IoU=0.7· 2023-11-28
    23.32
    best: 33.9 (SG-DETR (w/ PT))
    SOTA
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Highlight DetectiononYouTube Highlights
    mAP· 2023-11-28
    77.4
    best: 78 (SG-DETR (w/ PT))
    SOTA
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • VideoonTACoS
    R@1,IoU=0.5· 2023-11-28
    36.39
    best: 46.79 (DeCafNet)
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Moment RetrievalonCharades-STA
    R@1 IoU=0.5· 2023-11-28
    59.25
    best: 71.1 (SG-DETR (w/ PT))
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Moment RetrievalonCharades-STA
    R@1 IoU=0.7· 2023-11-28
    36.64
    best: 52.8 (SG-DETR (w/ PT))
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Moment RetrievalonQVHighlights
    R@1 IoU=0.5· 2023-11-28
    63.55
    best: 76.59 (LLaVA-MR)
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Moment RetrievalonQVHighlights
    R@1 IoU=0.7· 2023-11-28
    47.47
    best: 61.48 (LLaVA-MR)
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Moment RetrievalonQVHighlights
    mAP· 2023-11-28
    43.18
    best: 58.8 (SG-DETR (w/ PT))
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Moment RetrievalonQVHighlights
    mAP@0.5· 2023-11-28
    63.37
    best: 76.2 (SG-DETR (w/ PT))
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464
  • Moment RetrievalonQVHighlights
    mAP@0.75· 2023-11-28
    42.67
    best: 60.8 (SG-DETR (w/ PT))
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464

Methodology1 result

  • 16konYouTube Highlights
    mAP· 2023-11-28
    77.4
    best: 78 (SG-DETR (w/ PT))
    SOTA
    Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionarXiv:2311.16464