Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion
Zesheng Wang, Alexandre Bruckert, Patrick Le Callet +1
Generating realistic listener facial motions in dyadic conversations remains challenging due to the high-dimensional action space and temporal dependency requirements. Existing app…
cs.CV2021
Where to look at the movies : Analyzing visual attention to understand movie editing
Alexandre Bruckert, Marc Christie, Olivier Le Meur
In the process of making a movie, directors constantly care about where the spectator will look on the screen. Shot composition, framing, camera movements or editing are tools comm…