The authors propose a part-anchored representation for text-conditioned human-object interaction (HOI) generation.
Part-anchored voting generates more faithful human-object interactions from text
PAMI grounds object motion relative to multiple body anchors, achieving 14.5% higher contact recall than prior methods.
Research Lab
Chuqiao Li · Xianghui Xie · Yong Cao · Andreas Geiger · Gerard Pons-Moll
Tübingen AI Center, University of Tübingen · Max Planck Institute for Informatics
Research Digest··2 min read
Li et al.
Why this paper
From Max Planck Institute for Informatics and Tübingen AI Center, University of Tübingen
In one line
PAMI uses part-anchored voting to generate text-conditioned human-object interactions with 14.5% higher contact recall than prior methods.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§