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/QD-DETR

QD-DETR

Reported on 12 benchmarks across 5 tasks · 1 paper · 10 SOTA

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

Computer Vision9 results

  • VideoonQVHighlights
    R@1,IoU=0.5· 2023-03-24
    62.4
    best: 71.42 (InternVideo2-6B)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • VideoonQVHighlights
    R@1,IoU=0.7· 2023-03-24
    44.98
    best: 56.45 (InternVideo2-6B)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • Video RetrievalonQVHighlights
    R@1,IoU=0.5· 2023-03-24
    62.4
    best: 71.42 (InternVideo2-6B)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • Video RetrievalonQVHighlights
    R@1,IoU=0.7· 2023-03-24
    44.98
    best: 56.45 (InternVideo2-6B)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • Highlight DetectiononTvSum
    mAP· 2023-03-24
    86.6
    best: 88 (FlashVTG)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • Highlight DetectiononQVHighlights
    Hit@1· 2023-03-24
    62.87
    best: 71.01 (FlashVTG)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • Video GroundingonQVHighlights
    R@1,IoU=0.5· 2023-03-24
    62.4
    best: 71.42 (InternVideo2-6B)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • Video GroundingonQVHighlights
    R@1,IoU=0.7· 2023-03-24
    44.98
    best: 56.45 (InternVideo2-6B)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • Highlight DetectiononQVHighlights
    mAP· 2023-03-24
    39.04
    best: 44.7 (SG-DETR (w/ PT))
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874

Methodology3 results

  • 16konTvSum
    mAP· 2023-03-24
    86.6
    best: 88 (FlashVTG)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • 16konQVHighlights
    Hit@1· 2023-03-24
    62.87
    best: 71.01 (FlashVTG)
    SOTA
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874
  • 16konQVHighlights
    mAP· 2023-03-24
    39.04
    best: 44.7 (SG-DETR (w/ PT))
    Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionarXiv:2303.13874