AI Paper Atlas

Research map / Benchmarks / PoseTrack2017

PoseTrack2017 leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on PoseTrack2017. Best mAP (val): 88 (PSTPose, AAAI 2026).

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.

PoseTrack2017 · mAP (val)

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

#mAP ↑MethodPaperTopic
188PSTPoseAttentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation
AAAI 2026 · Table 1
Human pose estimation
288GLSMamba-H
ViT-H
High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation
ICCV 2025 · Table 1
Human pose estimation
387.8DiffusionPose
ViT (COCO pretrained)
DiffusionPose: Markov-Optimized Diffusion Model for Human Pose Estimation
AAAI 2026 · Table 1
Human pose estimation
487.6VREMD
ViT-L
Optimizing Human Pose Estimation Through Focused Human and Joint Regions
AAAI 2025 · Table 1
Human pose estimation
587.5CM-Pose
ViT
Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation
AAAI 2025 · Table: PoseTrack2017 quantitat
Human pose estimation
686.4DiffPoseDiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation
ICCV 2023 · Table 1
Human pose estimation
785.9TDMI-ST
HRNet-W48
Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video
CVPR 2023 · Table 1
Human pose estimation
885.6DSTA
ViT-H
Video-Based Human Pose Regression via Decoupled Space-Time Aggregation
CVPR 2024 · Table 1
Human pose estimation
984.8FAMI-Pose
HRNet-W48
Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation
CVPR 2022 · Table 1
Human pose estimation
1083.8Our full model
HRNet
Combining Detection and Tracking for Human Pose Estimation in Videos
CVPR 2020 · Ablation study on components
Human pose estimation
3 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.