3 papers
cs.CV2026
ReactionMamba: Generating Short & Long Human Reaction Sequences
Hajra Anwar Beg, Baptiste Chopin, Hao Tang +1
We present ReactionMamba, a novel framework for generating long 3D human reaction motions. Reaction-Mamba integrates a motion VAE for efficient motion encoding with Mamba-based sta…
cs.CV2026
Localized Latent Editing for Dose-Response Modeling in Botulinum Toxin Injection Planning
Estèphe Arnaud, Mohamed Daoudi, Pierre Guerreschi
Botulinum toxin (Botox) injections are the gold standard for managing facial asymmetry and aesthetic rejuvenation, yet determining the optimal dosage remains largely intuitive, oft…
cs.CV2025
REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge
Siyang Song, Micol Spitale, Xiangyu Kong +12
In dyadic interactions, a broad spectrum of human facial reactions might be appropriate for responding to each human speaker behaviour. Following the successful organisation of the…