Pose Estimation on COCO (Common Objects in Context)

30개 결과 · ⬇ CSV · JSON

Rank	Model	AP	AR	AP50	AP75	APL	APM	Paper	Code	Year
1	OmniPose (WASPv2)	79.5	81.9	93.6	85.9	84.6	76	OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation	bmartacho/OmniPose	2021
2	MetaPrompt-SD	79.0	–	–	–	–	–	Harnessing Diffusion Models for Visual Perception with Meta Prompts	fudan-zvg/meta-prompts	2023
3	Hulk(Finetune, ViT-L)	78.7	–	–	–	–	–	Hulk: A Universal Knowledge Translator for Human-Centric Tasks	opengvlab/humanbench · opengvlab/hulk	2023
4	BUCTD (PETR, with generative sampling)	77.8	–	–	–	–	–	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
5	Hulk(Finetune, ViT-B)	77.5	–	–	–	–	–	Hulk: A Universal Knowledge Translator for Human-Centric Tasks	opengvlab/humanbench · opengvlab/hulk	2023
6	I²R-Net (1st stage:HRFormer-B)	77.3	82.1	91	83.6	84.5	73	I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation	leijue222/Intra-and-Inter-Human-Relation-Network-for-MPEE	2022
7	PATH (Partial FT)	77.1	–	–	–	–	–	HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining	opengvlab/humanbench	2023
8	SOLIDER (swin-B)	76.6	81.5	–	–	–	–	Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks	modelscope/modelscope · tinyvision/SOLIDER · hasanirtiza/Pedestron · +1	2023
9	PEFORMER-Xcit-dino-p8	72.6	79.4	–	–	–	–	PE-former: Pose Estimation Transformer	padeler/pe-former	2021
10	BUCTD (PETR, with generative sampling)	–	–	–	–	83.7	74.2	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
11	OmniPose (WASPv2)	79.5	81.9	93.6	85.9	84.6	76	OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation	bmartacho/OmniPose	2021
12	MetaPrompt-SD	79.0	–	–	–	–	–	Harnessing Diffusion Models for Visual Perception with Meta Prompts	fudan-zvg/meta-prompts	2023
13	Hulk(Finetune, ViT-L)	78.7	–	–	–	–	–	Hulk: A Universal Knowledge Translator for Human-Centric Tasks	opengvlab/humanbench · opengvlab/hulk	2023
14	BUCTD (PETR, with generative sampling)	77.8	–	–	–	–	–	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023
15	Hulk(Finetune, ViT-B)	77.5	–	–	–	–	–	Hulk: A Universal Knowledge Translator for Human-Centric Tasks	opengvlab/humanbench · opengvlab/hulk	2023
16	I²R-Net (1st stage:HRFormer-B)	77.3	82.1	91	83.6	84.5	73	I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation	leijue222/Intra-and-Inter-Human-Relation-Network-for-MPEE	2022
17	PATH (Partial FT)	77.1	–	–	–	–	–	HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining	opengvlab/humanbench	2023
18	SOLIDER (swin-B)	76.6	81.5	–	–	–	–	Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks	modelscope/modelscope · tinyvision/SOLIDER · hasanirtiza/Pedestron · +1	2023
19	PEFORMER-Xcit-dino-p8	72.6	79.4	–	–	–	–	PE-former: Pose Estimation Transformer	padeler/pe-former	2021
20	BUCTD (PETR, with generative sampling)	–	–	–	–	83.7	74.2	Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity	amathislab/BUCTD	2023