Spotlight Talks

Talks

Session 1: 11:00am-12:00pm

1. Zsolt Kira, Continual Open-World Learning in the Era of Foundation Models

2. Helge Rhodin, Digital Humans for Science

3. Fabio Galasso, Learning human motion representations with uncertainty

4. Andrea Tagliasacchi, Towards mass-adoption of Neural Radiance Fields

5. Hilde Kuehne, Multimodal Embedding Learning for Video Understanding

6. Gul Varol, Is Human Motion a Language without Words?

7. Sergey Tulyakov, Towards Neural Game Engines

Session 2: 2:00pm-3:00pm

8. Miaomiao Liu, Scalable Unsupervised 3D Object Centric Learning from RGB-D Sequences

9. Tanmay Gupta (Ani Kembhavi to present on behalf), The beginning of the end of end-to-end

10. Fisher Yu, Better 4D Scene Understanding with Less Hassle

11. Xinlei Chen, What's Next After Masked Autoencoders?

12. Ioannis Gkioulekas, Interferometric computational imaging

13. Lamberto Ballan, Exploiting Proximity-Aware Tasks for Embodied Social Navigation

14. Ishan Misra, The effectiveness of SSL for multimodal learning and segmentation