Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/BBox-Mask-Pose 2x

BBox-Mask-Pose 2x

Reported on 10 benchmarks across 6 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 Vision6 results

Pose EstimationonOCHuman
Test AP· uses extra data· 2024-12-02
48.3
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
Pose EstimationonOCHuman
Validation AP· uses extra data· 2024-12-02
48.6
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
Pose EstimationonOCHuman
Test AP· uses extra data· 2024-12-02
48.3
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
Pose EstimationonOCHuman
Validation AP· uses extra data· 2024-12-02
48.6
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
Instance SegmentationonOCHuman
AP· 2024-12-02
32.4
best: 55.2 (Pose2Seg (plus ground-truth keypoints))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
Human Instance SegmentationonOCHuman
AP· 2024-12-02
32.4
best: 55.2 (Pose2Seg (plus ground-truth keypoints))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562

Methodology4 results

3DonOCHuman
Test AP· uses extra data· 2024-12-02
48.3
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
3DonOCHuman
Validation AP· uses extra data· 2024-12-02
48.6
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
3DonOCHuman
Test AP· uses extra data· 2024-12-02
48.3
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
3DonOCHuman
Validation AP· uses extra data· 2024-12-02
48.6
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562

Audio4 results

1 Image, 2*2 StitchionOCHuman
Test AP· uses extra data· 2024-12-02
48.3
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
1 Image, 2*2 StitchionOCHuman
Validation AP· uses extra data· 2024-12-02
48.6
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
1 Image, 2*2 StitchionOCHuman
Test AP· uses extra data· 2024-12-02
48.3
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
1 Image, 2*2 StitchionOCHuman
Validation AP· uses extra data· 2024-12-02
48.6
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562

Knowledge Base2 results

2D Human Pose EstimationonOCHuman
Test AP· uses extra data· 2024-12-02
48.3
SOTA
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562
2D Human Pose EstimationonOCHuman
Validation AP· uses extra data· 2024-12-02
48.6
SOTA
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle arXiv:2412.01562