Spotlight Talks
Talks
Session 1: 11:00am-12:00pm
Zsolt Kira, Continual Open-World Learning in the Era of Foundation Models
Helge Rhodin, Digital Humans for Science
Fabio Galasso, Learning human motion representations with uncertainty
Andrea Tagliasacchi, Towards mass-adoption of Neural Radiance Fields
Hilde Kuehne, Multimodal Embedding Learning for Video Understanding
Gul Varol, Is Human Motion a Language without Words?
Sergey Tulyakov, Towards Neural Game Engines
Session 2: 2:00pm-3:00pm
Miaomiao Liu, Scalable Unsupervised 3D Object Centric Learning from RGB-D Sequences
Tanmay Gupta (Ani Kembhavi to present on behalf), The beginning of the end of end-to-end
Fisher Yu, Better 4D Scene Understanding with Less Hassle
Xinlei Chen, What's Next After Masked Autoencoders?
Ioannis Gkioulekas, Interferometric computational imaging
Lamberto Ballan, Exploiting Proximity-Aware Tasks for Embodied Social Navigation
Ishan Misra, The effectiveness of SSL for multimodal learning and segmentation