AI Center Seminar - AI for Science series - Dr. Gül Varol "3D human motion & language"

The talk is jointly organized by the EPFL AI Center and the Mathis Group for Computational Neuroscience and AI. 

Hosting professor: Prof. Alexander Mathis

For on-site logistics, please use the following form to register (with your EPFL email address): Here. 
The talk will be followed by a coffee session.

_________________

Title
3D human motion & language

Abstract
This talk will summarize our recent works on bridging the gap between natural language and 3D human motions. In particular, I will show results on text-to-motion synthesis, i.e., text-conditioned generative models for controllable motion synthesis, with a special focus on compositionality to handle finegrained textual descriptions. I will further describe the follow-up works on text-to-motion retrieval and text-based motion editing. The relevant reading materials are ACTOR, TEMOS, TMR, STMC [Petrovich 2021, 2022, 2023, 2024] and TEACH, SINC, MotionFix [Athanasiou 2022, 2023, 2024].

Bio
Gul Varol is a permanent researcher in the IMAGINE team at Ecole des Ponts ParisTech. Previously, she was a postdoctoral researcher at the University of Oxford (VGG). She obtained her PhD from the WILLOW team of Inria Paris and Ecole Normale Superieure (ENS). Her thesis received PhD awards from ELLIS and AFRIF. She regularly serves as an Area Chair at major computer vision conferences, and has served as a Program Chair at ECCV'24. Her research interests cover vision and language applications, including video representation learning, human motion synthesis, and sign languages.