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/TAL-Net

TAL-Net

Reported on 32 benchmarks across 4 tasks · 1 paper · 28 SOTA

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

Computer Vision24 results

  • VideoonTHUMOS’14
    Avg mAP (0.3:0.7)· 2018-04-20
    39.8
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • VideoonTHUMOS’14
    mAP IOU@0.2· 2018-04-20
    57.1
    best: 72.29 (TSP)
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • VideoonTHUMOS’14
    mAP IOU@0.3· 2018-04-20
    53.2
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • VideoonTHUMOS’14
    mAP IOU@0.4· 2018-04-20
    48.5
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • VideoonTHUMOS’14
    mAP IOU@0.5· 2018-04-20
    42.8
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • VideoonTHUMOS’14
    mAP IOU@0.6· 2018-04-20
    33.8
    best: 71 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • VideoonTHUMOS’14
    mAP IOU@0.7· 2018-04-20
    20.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    Avg mAP (0.3:0.7)· 2018-04-20
    39.8
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.2· 2018-04-20
    57.1
    best: 72.29 (TSP)
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.3· 2018-04-20
    53.2
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.4· 2018-04-20
    48.5
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.5· 2018-04-20
    42.8
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.6· 2018-04-20
    33.8
    best: 71 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.7· 2018-04-20
    20.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    Avg mAP (0.3:0.7)· 2018-04-20
    39.8
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.2· 2018-04-20
    57.1
    best: 72.29 (TSP)
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.3· 2018-04-20
    53.2
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.4· 2018-04-20
    48.5
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.5· 2018-04-20
    42.8
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.6· 2018-04-20
    33.8
    best: 71 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.7· 2018-04-20
    20.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • VideoonTHUMOS’14
    mAP IOU@0.1· 2018-04-20
    59.8
    best: 74.02 (TSP)
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.1· 2018-04-20
    59.8
    best: 74.02 (TSP)
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.1· 2018-04-20
    59.8
    best: 74.02 (TSP)
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667

Methodology8 results

  • Zero-Shot LearningonTHUMOS’14
    Avg mAP (0.3:0.7)· 2018-04-20
    39.8
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.2· 2018-04-20
    57.1
    best: 72.29 (TSP)
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.3· 2018-04-20
    53.2
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.4· 2018-04-20
    48.5
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.5· 2018-04-20
    42.8
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.6· 2018-04-20
    33.8
    best: 71 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.7· 2018-04-20
    20.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    SOTA
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.1· 2018-04-20
    59.8
    best: 74.02 (TSP)
    Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationarXiv:1804.07667