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/VSTAM

VSTAM

Reported on 11 benchmarks across 6 tasks

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

Methodology8 results

  • 3DonUA-DETRAC
    mAP
    90.39
  • 3DonImageNet VID
    MAP
    91.1
    best: 93.2 (YOLOV++)
  • 2D ClassificationonUA-DETRAC
    mAP
    90.39
  • 2D ClassificationonImageNet VID
    MAP
    91.1
    best: 93.2 (YOLOV++)
  • 2D Object DetectiononUA-DETRAC
    mAP
    90.39
  • 2D Object DetectiononImageNet VID
    MAP
    91.1
    best: 93.2 (YOLOV++)
  • 16konUA-DETRAC
    mAP
    90.39
  • 16konImageNet VID
    MAP
    91.1
    best: 93.2 (YOLOV++)

Computer Vision3 results

  • Object DetectiononUA-DETRAC
    mAP
    90.39
  • Object DetectiononImageNet VID
    MAP
    91.1
    best: 93.2 (YOLOV++)
  • Video Instance SegmentationonYouTube-VIS validation
    mask AP
    39
    best: 68.9 (CAVIS(ViT-L, Online))