moteur de recherche

Séminaire A3SI - Bryan Russell
Séminaire A3SI - Bryan Russell
2-Oct-2019 14:00
Age: 108 days

Le prochain séminaire de l'équipe A3SI du LIGM aura lieu mercredi 2 octobre à 14h à l'ENPC (salle B412, Aile Becquerel, bâtiment Coriolis). Nous aurons le plaisir d'écouter Bryan Russell nous présenter ses travaux sur "Moments and Bounces"

Abstract: In my talk, I will describe recent work on two challenging tasks in video understanding: (1) localizing moments in videos given a natural language query, and (2) modeling and generating bounce interactions in real-world scenes. For localizing moments in videos with natural language, I will describe an approach that reason over temporal language. In addition, I will describe an approach that extends to searching over a large video corpus. For modeling bounces, I will describe our model that learns end-to-end, starting from sensor inputs, to predict post-bounce trajectories and infer two underlying physical properties that govern bouncing - restitution and effective collision normals. For generating bounces, I will describe an approach that learns to "correct" traditional simulation output, generated with incomplete and imprecise world information, to obtain context-specific, visually plausible re-simulated output, a process we call neural re-simulation.

<- Back to: Accueil