AI Paper Atlas

Research map / 3D vision / Human pose estimation

Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation

Hongwei Fang, Jiahang Cai, Xun Wang, Wenwu Yang

CVPR 2026 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 1 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 temporal aggregate-and-restore to ViTPoseViTPose ViT-B · PoseTrack2017 valmAP: 81.7 -> 84.0Improved
add temporal aggregate-and-restore to ViTPoseViTPose ViT-H · PoseTrack2017 valmAP: 84.7 -> 86.8Improved
joint-specific temporal modeling (JTA) instead of cross-attention over aux frames (ablation)TAR-ViTPose ViT-B · PoseTrack2017 valmAP: 82.8 -> 84.0Improved
generic self/cross-attention variants (ablation)TAR-ViTPose ViT-B · PoseTrack2017 valmAP: 82.2 / 82.6 / 82.8 vs baseline 81.7No clear effect
add Global Restoring Attention (GRA) (ablation)TAR-ViTPose ViT-B · PoseTrack2017 valmAP: 70.3 -> 84.0Improved
add mask-aware attention to JTA (ablation)TAR-ViTPose ViT-B · PoseTrack2017 valmAP: 82.6 -> 84.0Improved
use ground-truth boxes instead of detector boxesTAR-ViTPose ViT-H · PoseTrack2017 valmAP: 86.8 -> 90.3Improved
use ViT-S TAR-ViTPose over PoseWarper for speedTAR-ViTPose · PoseTrack2017 runtimeFPS: 52 -> 413Improved

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