AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Human Motion Forecasting in Dynamic Domain Shifts: A Homeostatic Continual Test-time Adaptation Framework

Qiongjie Cui, Huaijiang Sun, Bin Li, Jianfeng Lu, Weiqing Li

ECCV 2024 · Continual learning › Domain and prompt-based · approach: Continual 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
update only domain-sensitive parameters (isolated update) instead of all parameters (ablation)HoCoTTA · Human3.6M to GRABMPJPE at 1000ms (mm): 127.0 -> 119.2Improved
use 24 novel-domain augmentations instead of 16 (ablation)HoCoTTA · Human3.6M to GRABMPJPE at 1000ms (mm): 123.4 -> 119.2Improved
increase augmentations from 24 to 32 (ablation)HoCoTTA · Human3.6M to GRABMPJPE at 1000ms (mm): 119.2 -> 120.3No clear effect
set isolation quantile tau to 0.2 instead of 0.15 (ablation)HoCoTTA · Human3.6M to GRABMPJPE at 1000ms (mm): 122.1 -> 119.2Improved
raise learning rate from 0.001 to 0.0015 (ablation)HoCoTTA · Human3.6M to GRABMPJPE at 1000ms (mm): 119.2 -> 124.5Hurt
raise EMA momentum from 0.99 to 0.995 (ablation)HoCoTTA · Human3.6M to GRABMPJPE at 1000ms (mm): 119.2 -> 122.7Hurt
HoCoTTA vs H/P-TTP on novel dataset adaptationH/P-TTP · Human3.6M to GRAB, A1 passingMPJPE at 400ms (mm): 45.4 -> 37.7Improved
HoCoTTA vs H/P-TTP on unseen categories and subjectsH/P-TTP · Human3.6M unseen categoriesMPJPE at 1000ms (mm): 102.5 -> 99.6Improved
HoCoTTA vs H/P-TTP at short horizon on CMU Mocap unseen categoriesH/P-TTP · CMU Mocap unseen categoriesMPJPE at 160ms (mm): 13.4 vs 13.5No clear effect
HoCoTTA vs siMLPe backbone under standard splitssiMLPe · Human3.6M (setup-1)MPJPE at 1000ms (mm): 109.4 -> 98.4Improved

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