AI Paper Atlas

Research map / 3D vision / Human pose estimation

Encoder-Decoder With Multi-Level Attention for 3D Human Shape and Pose Estimation

Ziniu Wan, Zhengjia Li, Maoqing Tian, Jianbo Liu, Shuai Yi, Hongsheng Li

ICCV 2021 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 97 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 Spatial-Temporal Encoder (parallel block) to the CNN with iterative decoder (ablation)CNN + Iterative · 3DPWPA-MPJPE: 52.2 -> 47.5Improved
add Kinematic Topology Decoder to the CNN encoder (ablation)CNN + Iterative · 3DPWPA-MPJPE: 52.2 -> 50.9Improved
add Kinematic Topology Decoder to the CNN encoder (ablation)CNN + Iterative · 3DPWMPJPE: 87.5 -> 88.0Hurt
add KTD on top of the STE encoder (ablation)CNN+STE + Iterative · 3DPWPA-MPJPE: 47.5 -> 45.7Improved
add KTD on top of the STE encoder (ablation)CNN+STE + Iterative · 3DPWMPJPE: 80.2 -> 79.1Improved
add temporal-only attention encoder (TE) (ablation)CNN + Iterative · 3DPWPA-MPJPE: 52.2 -> 51.1Improved
add spatial-only attention encoder (SE) (ablation)CNN + Iterative · 3DPWPA-MPJPE: 52.2 -> 49.8Improved
use parallel block with attentive addition instead of series block (ablation)CNN+STE + Iterative · 3DPWPA-MPJPE: 48.5 -> 47.5Improved
add attentive weights (v2) to parallel block instead of mean (v1) (ablation)CNN+STE parallel + Iterative · 3DPWPA-MPJPE: 48.1 -> 47.5Improved
use parallel block instead of coupling block (ablation)CNN+STE + Iterative · 3DPWPA-MPJPE: 49.3 -> 47.5Improved
add temporal modeling via coupling block over spatial-only encoder (ablation)CNN+SE + Iterative · 3DPWPA-MPJPE: 49.8 -> 49.3No clear effect
use vanilla transformer decoder instead of iterative regressor (ablation)CNN+STE · 3DPWPA-MPJPE: 47.5 -> 47.7No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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