paper-with-me

Pose Estimation 벤치마크

Pose Estimation on OCHuman

58개 결과 · ⬇ CSV · JSON

Test AP

1.5 24.45 47.4 70.35 93.3 2016-11 2026-09 Associative Embedding+ — 32.8 (2016-11-16) Associative Embedding — 29.5 (2016-11-16) Associative Embedding+ — 32.8 (2016-11-16) Associative Embedding — 29.5 (2016-11-16) Associative Embedding+ — 32.8 (2016-11-16) Associative Embedding — 29.5 (2016-11-16) RMPE — 30.7 (2016-12-01) RMPE — 30.7 (2016-12-01) RMPE — 30.7 (2016-12-01) ResNet-152 — 33.3 (2018-04-17) ResNet-50 — 29.5 (2018-04-17) ResNet-152 — 33.3 (2018-04-17) ResNet-50 — 29.5 (2018-04-17) ResNet-152 — 33.3 (2018-04-17) ResNet-50 — 29.5 (2018-04-17) HGG (AE+) — 36.0 (2020-07-23) HGG (AE+) — 36.0 (2020-07-23) HGG (AE+) — 36.0 (2020-07-23) MIPNet (HRNet-W48) — 42.5 (2021-01-27) HRNet-W48 — 37.2 (2021-01-27) MIPNet (HRNet-W48) — 42.5 (2021-01-27) HRNet-W48 — 37.2 (2021-01-27) MIPNet (HRNet-W48) — 42.5 (2021-01-27) HRNet-W48 — 37.2 (2021-01-27) CID (HRNet-W48) — 45.0 (2022-01-01) CID (HRNet-W48) — 45.0 (2022-01-01) CID (HRNet-W48) — 45.0 (2022-01-01) ViTPose (ViTAE-G, GT bounding boxes) — 93.3 (2022-04-26) ViTPose (ViTAE-G, GT bounding boxes) — 93.3 (2022-04-26) ViTPose (ViTAE-G, GT bounding boxes) — 93.3 (2022-04-26) UniHCP (direct eval) — 87.4 (2023-03-06) UniHCP (direct eval) — 87.4 (2023-03-06) UniHCP (direct eval) — 87.4 (2023-03-06) RTMPose(RTMPose-l, GT bounding boxes) — 80.3 (2023-03-13) RTMPose(RTMPose-l, GT bounding boxes) — 80.3 (2023-03-13) RTMPose(RTMPose-l, GT bounding boxes) — 80.3 (2023-03-13) BUCTD (CID-W32) — 47.2 (2023-06-13) BUCTD (CID-W32) — 47.2 (2023-06-13) BUCTD (CID-W32) — 47.2 (2023-06-13) HQNet (ViT-L) — 45.6 (2023-12-09) HQNet (ResNet-50) — 40.0 (2023-12-09) HQNet (ViT-L) — 45.6 (2023-12-09) HQNet (ResNet-50) — 40.0 (2023-12-09) HQNet (ViT-L) — 45.6 (2023-12-09) HQNet (ResNet-50) — 40.0 (2023-12-09) BBox-Mask-Pose 2x — 48.3 (2024-12-02) MaskPose-b — 45.0 (2024-12-02) BBox-Mask-Pose 2x — 48.3 (2024-12-02) MaskPose-b — 45.0 (2024-12-02) BBox-Mask-Pose 2x — 48.3 (2024-12-02) MaskPose-b — 45.0 (2024-12-02) PoseBH-H — 87.0 (2025-05-23) PoseBH-H — 87.0 (2025-05-23) PoseBH-H — 87.0 (2025-05-23) PMPose — 1.5 (2026-01-21) Associative Embedding+ — 32.8 (2016-11-16) ResNet-152 — 33.3 (2018-04-17) HGG (AE+) — 36.0 (2020-07-23) MIPNet (HRNet-W48) — 42.5 (2021-01-27) CID (HRNet-W48) — 45.0 (2022-01-01) ViTPose (ViTAE-G, GT bounding boxes) — 93.3 (2022-04-26)
RankModel Test APValidation AP Extra Training Data PaperCodeYear
1 ViTPose (ViTAE-G, GT bounding boxes) 93.392.8 ✓ ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation huggingface/transformers · vitae-transformer/vitpose · vitae-transformer/qformer · +3 2022
2 UniHCP (direct eval) 87.4– UniHCP: A Unified Model for Human-Centric Perceptions opengvlab/unihcp 2023
3 PoseBH-H 87.086.0 ✓ PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation uyoung-jeong/PoseBH 2025
4 RTMPose(RTMPose-l, GT bounding boxes) 80.380.5 ✓ RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose open-mmlab/mmpose 2023
5 BBox-Mask-Pose 2x 48.348.6 ✓ Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle MiraPurkrabek/BBoxMaskPose 2024
6 BUCTD (CID-W32) 47.247.7 Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity amathislab/BUCTD 2023
7 HQNet (ViT-L) 45.6– You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception lishuhuai527/coco-unihuman 2023
8 CID (HRNet-W48) 45.046.1 Contextual Instance Decoupling for Robust Multi-Person Pose Estimation kennethwdk/cid 2022
8 MaskPose-b 45.045.3 ✓ Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle MiraPurkrabek/BBoxMaskPose 2024
10 MIPNet (HRNet-W48) 42.542.0 Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation rawalkhirodkar/MIPNet 2021
1–10 / 58 다음 → 페이지당 10 20 50 100