ACM Multimedia Workshop on Multimodal Conversational AI

16th October, 2pm CET


Program

All pre-recorded video will be published online for on-demand streaming. No time slot will be allocated for showing these videos. All participants are encouraged to watch the video presentations before going to the corresponding live Question and Answer (QA) sessions.

The second Paper QA session is scheduled to run 10 hours after the first session to cover a different time zone.


08:00 am (ET) Welcome

08:10 am (ET) Keynote: Response Generation and Retrieval in Multimodal Conversational AI, Verena Rieser
(Heriot-Watt University, UK)

9:00 am (ET) Papers Q&A session time-zone 1

10:00 am (ET) Keynote: Augmenting Machine Intelligence with Multimodal Information, Zhou Yu
(University of California at Davies, USA)

11:00 am (ET) Panel: Vision and Challenges in Multimodal Conversational AI

Moderator: Alex Hauptmann

Members:

  • Alex Rudinicky, Carnegie Mellon University, USA

  • Verena Rieser, Heriot-Watt University, UK

  • Zhou Yu, University of California at Davies, USA

  • Xavier Alameda-Pineda, INRIA, France

12:30 am (ET) Closing remarks

19:00 am (ET) Papers Q&A session time-zone 2