AI Paper Atlas

Research map / 3D vision / Human pose estimation

Attentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation

Sifan Wu, Haipeng Chen, Yingda Lyu, Shaojing Fan, Zhigang Wang, Zhenguang Liu, Yingying Jiao

AAAI 2026 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 0 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 Discriminative Feature Enhancement (DFE) (ablation)PSTPose · PoseTrack2017 valmAP: 86.5 -> 88.0Improved
add Feature Cluster Grouping (FCG) (ablation)PSTPose · PoseTrack2017 valmAP: 86.2 -> 88.0Improved
add Deformable Spatiotemporal Fusion (DSF) (ablation)PSTPose · PoseTrack2017 valmAP: 86.4 -> 88.0Improved
add all three modules to standard-attention baseline (ablation)PSTPose · PoseTrack2017 valmAP: 84.2 -> 88.0Improved
use PSTPose instead of TPSD-ViT (best prior)video pose estimation · PoseTrack2017 valmAP: 86.7 -> 88.0Improved
use PSTPose instead of TPSD-ViTvideo pose estimation · PoseTrack2018 valmAP: 84.2 -> 84.9Improved
use PSTPose instead of JMPosevideo pose estimation · PoseTrack21mAP: 84.0 -> 84.8Improved
use PSTPose instead of JMPose on head keypointvideo pose estimation · PoseTrack2017 valHead AP: 90.7 -> 90.0Hurt

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