AI Paper Atlas

Research map / Benchmarks / CrowdPose

CrowdPose leaderboard

25 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CrowdPose. Best AP: 79.4 (VisionLLM v2, NeurIPS 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CrowdPose · AP

25 papers, each with its best reported number for its own method; higher is better.

#AP ↑MethodPaperTopic
179.4VisionLLM v2
Swin-T
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
NeurIPS 2024 · Pose estimation table
Multimodal LLMs
278.5BUCTD-CoAM-W48++σ
HRNet-W48, PETR conditions
Rethinking Pose Estimation in Crowds: Overcoming the Detection Information Bottleneck and Ambiguity
ICCV 2023 · Table 2
Human pose estimation
376.6ED-Pose
Swin-L*
Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
ICLR 2023 · CrowdPose comparison table
CNN features
476.2TokenCLIPoseSeeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction
NeurIPS 2024 · Table 3
Open-set and few-shot detection
575.8CIGPose-x (384x288)CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation
CVPR 2026 · Table 3
Human pose estimation
675.1DETRPose-X
HGNetv2-B5
DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints
ECCV 2026 · Table 4
Human pose estimation
774.91K-MIM
SwinV2-B
Revealing the Dark Secrets of Masked Image Modeling
CVPR 2023 · Table: geometric and motion ta
Attention and transformers
874.3RSGNet
HRNet-W32
RSGNet: Relation based Skeleton Graph Network for Crowded Scenes Pose Estimation
AAAI 2021 · Table 1
Human pose estimation
974.1GroupPose
Swin-L
Group Pose: A Simple Baseline for End-to-End Multi-Person Pose Estimation
ICCV 2023 · Table 3
Human pose estimation
1073.5TopoDA
Swin-T
Learning Topology-Aware Dynamic Associations for Robust Multi-Person Pose Estimation
AAAI 2026 · Table 1
Human pose estimation
15 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.