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/SHARP

SHARP

Reported on 10 benchmarks across 8 tasks · 1 paper · 8 SOTA

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

Computer Vision3 results

  • VideoonH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037
  • Temporal Action LocalizationonH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037
  • Action LocalizationonH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037

Time Series3 results

  • Action DetectiononH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037
  • Action RecognitiononH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037
  • Action RecognitiononH2O (2 Hands and Objects)
    Actions Top-1· 2024-08-19
    91.73
    best: 93.39 (HandFormer-B/21x8)
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037

Robots2 results

  • Activity RecognitiononH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037
  • Activity RecognitiononH2O (2 Hands and Objects)
    Actions Top-1· 2024-08-19
    91.73
    best: 93.39 (HandFormer-B/21x8)
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037

Methodology1 result

  • Zero-Shot LearningonH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037

Natural Language Processing1 result

  • 3D Action RecognitiononH2O (2 Hands and Objects)
    Accuracy· 2024-08-19
    91.73
    best: 94.77 (CHASE(STSA-Net))
    SOTA
    SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action RecognitionarXiv:2408.10037