PAMI Boosts Text-to-HOI Motion Generation with Part-Anchored Objects

PAMI anchors object motion to body parts and combines anchor predictions via voting, improving contact accuracy in text-generated human-object interaction motion by 14.5%.

2026-10-09 ~ 2026-10-09 · 2 related posts

• PAMI anchors object motion to body parts for text-to-HOI, +14.5% contact recall — Chuqiao Li · 2026-10-09
• PAMI: part-anchored motion lifts contact recall 14.5% in text-to-HOI generation — _akhaliq · 2026-10-09