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/LLaVA-MR

LLaVA-MR

Reported on 9 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision9 results

  • Moment RetrievalonQVHighlights
    R@1 IoU=0.5· 2024-11-21
    76.59
    SOTA
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • Moment RetrievalonQVHighlights
    R@1 IoU=0.7· 2024-11-21
    61.48
    SOTA
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • VideoonActivityNet Captions
    R@1,IoU=0.5· 2024-11-21
    55.16
    best: 60.67 (GVL (paragraph-level))
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • VideoonActivityNet Captions
    R@1,IoU=0.7· 2024-11-21
    35.68
    best: 38.55 (GVL (paragraph-level))
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • Moment RetrievalonCharades-STA
    R@1 IoU=0.5· 2024-11-21
    70.65
    best: 71.1 (SG-DETR (w/ PT))
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • Moment RetrievalonCharades-STA
    R@1 IoU=0.7· 2024-11-21
    49.58
    best: 52.8 (SG-DETR (w/ PT))
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • Moment RetrievalonQVHighlights
    mAP· 2024-11-21
    52.73
    best: 58.8 (SG-DETR (w/ PT))
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • Moment RetrievalonQVHighlights
    mAP@0.5· 2024-11-21
    69.41
    best: 76.2 (SG-DETR (w/ PT))
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505
  • Moment RetrievalonQVHighlights
    mAP@0.75· 2024-11-21
    54.4
    best: 60.8 (SG-DETR (w/ PT))
    LLaVA-MR: Large Language-and-Vision Assistant for Video Moment RetrievalarXiv:2411.14505