AI Paper Atlas

Research map / 3D vision / Human pose estimation

High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation

Runyang Feng, Hyung Jin Chang, Tze Ho Elden Tse, Boeun Kim, Yi Chang, Yixing Gao

ICCV 2025 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Global Spatiotemporal Mamba to backbone (ablation)GLSMamba-B · PoseTrack2017 val (ablation)mAP: 74.2 -> 86.0Improved
add Local Refinement Mamba (ablation)GLSMamba-B · PoseTrack2017 val (ablation)mAP: 86.0 -> 86.9Improved
add space-wise scan to unified scan (ablation)STS6D · PoseTrack2017 val (scan ablation)mAP: 85.8 -> 86.5Improved
add time-wise scan to unified + space-wise (ablation)STS6D · PoseTrack2017 val (scan ablation)mAP: 86.5 -> 86.9Improved
add STMM instead of simple addition merging (ablation)GSM · PoseTrack2017 val (scan ablation)mAP: 86.2 -> 86.9Improved
use 1/4 resolution instead of 1/16 (ablation)GLSMamba-B · PoseTrack2017 val (resolution study)mAP: 85.7 -> 86.9Improved
use 1/8 resolution instead of 1/16 (ablation)Transformer · PoseTrack2017 val (resolution study)mAP: 84.2 -> 84.8Improved
use 1/4 resolution with Transformer (ablation)Transformer · PoseTrack2017 val (resolution study)mAP: OOM vs 138.9 GFLOPsHurt
GLSMamba-B instead of TDMITDMI · PoseTrack2017 valmAP: 85.7 -> 86.9Improved
GLSMamba-B instead of DiffPoseDiffPose · PoseTrack2017 valmAP: 86.4 -> 86.9Improved
GLSMamba-B instead of FAMI-PoseFAMI-Pose · Sub-JHMDBmAP: 96.0 -> 97.9Improved
GLSMamba-B instead of DeciWatchDeciWatch · Sub-JHMDBmAP: 98.8 -> 97.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy