AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Anatomical Domain Shifts: Test-time Heterogeneous Adaptation for 3D Human Pose Prediction

Qiongjie Cui, Pan Zhou, Jingjing Chen, Na Zhao

CVPR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 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
use anatomical segment-wise adaptation (TT-HA) instead of full-body HoCoTTAsiMLPe + TTA · H3.6M->GRAB setup-4 (RICH, setup-1)MPJPE 1000ms: 127.2 -> 119.4Improved
use TT-HA instead of HoCoTTAsiMLPe + TTA · GRAB unseen categoriesMPJPE 1000ms: 136.2 -> 132.2Improved
use TT-HA instead of HoCoTTAsiMLPe + TTA · GRAB unseen subjectsMPJPE 1000ms: 130.1 -> 127.7Improved
use TT-HA instead of HoCoTTAsiMLPe + TTA · CMU Mocap setup-1MPJPE 1000ms: 71.1 -> 68.5Improved
use TT-HA instead of HoCoTTAsiMLPe + TTA · GRAB setup-1MPJPE 400ms: 45.2 -> 44.3No clear effect
use TT-HA instead of HoCoTTAsiMLPe + TTA · H3.6M unseen categoriesMPJPE 160ms: 22.1 -> 22.4Hurt
add test-time adaptation (HoCoTTA) to siMLPesiMLPe · GRAB unseen subjectsMPJPE 1000ms: 155.9 -> 130.1Improved
set momentum eta to 0.95 instead of 0.92 (ablation)TT-HA · H3.6M->GRAB setup-4MPJPE 1000ms: 121.7 -> 117.1Improved
set momentum eta to 0.95 instead of 0.98 (ablation)TT-HA · H3.6M->GRAB setup-4MPJPE 1000ms: 120.6 -> 117.1Improved
set peak threshold tau to 12 instead of 10 (ablation)TT-HA · H3.6M->GRAB setup-4MPJPE 1000ms: 122.0 -> 117.1Improved
set peak threshold tau to 12 instead of 14 (ablation)TT-HA · H3.6M->GRAB setup-4MPJPE 1000ms: 121.6 -> 117.1Improved
set window size w to 36 instead of 48 (ablation)TT-HA · H3.6M->GRAB setup-4MPJPE 1000ms: 120.1 -> 117.1Improved

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