The first Workshop on
Visual Object-oriented Learning meets Interaction (VOLI):
Discovery, Representations, and Applications


October 24 @ ECCV 2022 Virtual


  • Home

Select your time zone
Default: Tel-Aviv Time (GMT/UTC+3)

  • Here is the ECCV Platform.
  • Please log in using your ECCV credentials, click "Workshops", then "Oct 24", find our workshop and click "Join Now".

Start End Event

Welcome and Introductions

Workshop Organizers (Kaichun Mo and Jiayuan Gu)

Equivariance: from Objects to Scenes


Kostas Daniilidis (UPenn)

Interacting with Neural Assets


Niloy Mitra (UCL & Adobe)

Physion: Evaluating Physical Prediction
from Vision in Humans and Machines


Judith Fan (UC San Diego)

Coffee Break

Slot Attention: Object Discovery in Images and Videos


Thomas Kipf (Google Brain)

Objects in 3D Scenes


Klaus Greff (Google Brain)

Emergence of Object Representation from Environmental Interaction


Stefano Soatto (UC Los Angeles & Amazon)

Lunch Break

Accepted Paper Spotlight Talks

Towards Structured Slots


Sungjin Ahn (KAIST)

Segmenting Unseen Objects for Robot Manipulation


Christopher Xie (Meta)

Object Perception through Interaction


Jeannette Bohg (Stanford)

Accepted Paper Poster Session

[GatherTown] [Instructions]

Learning Generic and Generalizable Object Manipulation Skills from Vision with ManiSkill2


Hao Su (US San Diego)

From Human-Scene Interaction to Human-Machine Teaming


Yixin Zhu (Peking Univ.)

Panel Discussion

Host: Yanchao Yang, Shubham Tulsiani
Panelists: XXX

Contact Info

E-mail: kaichun@cs.stanford.edu

Acknowledgements

Website template borrowed from: https://futurecv.github.io/ (Thanks to Deepak Pathak)