Pose Estimation on CrowdPose

36개 결과 · ⬇ CSV · JSON

Rank	Model	AP	AP50	AP75	APM	Test	AP Hard	AP Easy	AP Medium	Paper	Code	Year
1	BUCTD-W48 (w/cond. input from PETR, and generative sampling)	78.5	–	–	–	–	72.3	83.9	79.0	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
2	ViTPose-G	78.3	85.3	81.4	86.6	–	67.9	–	–	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	huggingface/transformers · vitae-transformer/vitpose · vitae-transformer/qformer · +3	2022
3	BUCTD-W48 (w/cond. input from PETR)	76.7	–	–	–	–	–	–	–	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
4	SwinV2-L 1K-MIM	75.5	–	–	–	–	–	–	–	Revealing the Dark Secrets of Masked Image Modeling	SwinTransformer/MIM-Depth-Estimation	2022
5	SwinV2-B 1K-MIM	74.9	–	–	–	–	–	–	–	Revealing the Dark Secrets of Masked Image Modeling	SwinTransformer/MIM-Depth-Estimation	2022
6	BUCTD-W48	72.9	–	–	–	–	–	–	–	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
7	OpenPifPaf	70.5	89.1	76.1	–	–	63.8	78.4	72.1	OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association	openpifpaf/openpifpaf · openpifpaf/openpifpafwebdemo · vita-epfl/openpifpaf · +3	2021
8	MIPNet (HRNet-W48)	70.0	–	–	71.1	–	59.4	–	–	Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation	rawalkhirodkar/MIPNet	2021
9	KAPAO-L	68.9	89.4	75.6	69.9	76.6	–	–	–	Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation	wmcnally/kapao	2021
10	KAPAO-M	67.1	88.8	73.4	68.1	75.2	–	–	–	Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation	wmcnally/kapao	2021
11	Hourglass-104	65.2	85.9	69.5	66.2	–	–	–	–	Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation	hellojialee/OffsetGuided	2021
12	KAPAO-S	63.8	87.7	69.4	64.8	72.1	–	–	–	Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation	wmcnally/kapao	2021
13	BUCTD-W48 (w/cond. input from PETR, and generative sampling)	78.5	–	–	–	–	72.3	83.9	79.0	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
14	ViTPose-G	78.3	85.3	81.4	86.6	–	67.9	–	–	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	huggingface/transformers · vitae-transformer/vitpose · vitae-transformer/qformer · +3	2022
15	BUCTD-W48 (w/cond. input from PETR)	76.7	–	–	–	–	–	–	–	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
16	SwinV2-L 1K-MIM	75.5	–	–	–	–	–	–	–	Revealing the Dark Secrets of Masked Image Modeling	SwinTransformer/MIM-Depth-Estimation	2022
17	SwinV2-B 1K-MIM	74.9	–	–	–	–	–	–	–	Revealing the Dark Secrets of Masked Image Modeling	SwinTransformer/MIM-Depth-Estimation	2022
18	BUCTD-W48	72.9	–	–	–	–	–	–	–	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
19	OpenPifPaf	70.5	89.1	76.1	–	–	63.8	78.4	72.1	OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association	openpifpaf/openpifpaf · openpifpaf/openpifpafwebdemo · vita-epfl/openpifpaf · +3	2021
20	MIPNet (HRNet-W48)	70.0	–	–	71.1	–	59.4	–	–	Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation	rawalkhirodkar/MIPNet	2021