W9: Advances in Language and Vision Research (ALVR)

Xin Wang, Jesse Thomason, Ronghang Hu, Xinlei Chen, Peter Anderson, Qi Wu, Asli Celikyilmaz, Jason Baldridge, William Yang Wang

Description Schedule External Website
Live Session: Jul 9 (15:20-00:10 GMT)
Live Session: Jul 10 (00:10-00:45 GMT)
Workshop on Advances in Language and Vision Research. Promoting the frontier of language and vision research and bringing researchers together to discuss real-world solutions in this area.

Time (PDT) Event Speakers
9 Jul, 8:20 AM-8:25 AM Opening Remarks Workshop Organizers
9 Jul, 8:25 AM-9:00 AM Grounding Natural Language to 3D Angel Chang
9 Jul, 9:00 AM-9:10 AM Live QA Angel Chang
9 Jul, 9:10 AM-9:45 AM Challenges in Evaluating Vision and Language Tasks Lucia Specia
9 Jul, 9:45 AM-9:55 AM Live QA Lucia Specia
9 Jul, 9:55 AM-10:30 AM Multimodal AI: Understanding Human Behaviors Louis-Philippe Morency
9 Jul, 10:30 AM-10:40 AM Live QA Louis-Philippe Morency
9 Jul, 10:50 AM-11:25 AM Robot Control in Situated Instruction Following Yoav Artzi
9 Jul, 11:25 AM-11:35 AM Live QA Yoav Artzi
9 Jul, 11:35 AM-11:45 AM VMT Challenge Xin Wang
9 Jul, 11:45 AM-12:10 PM VMT Challenge Talk VMT Challenge Winners
9 Jul, 12:10 PM-12:20 PM VMT Live QA VMT Challenge Winners
9 Jul, 1:30 PM-2:05 PM Augment Machine Intelligence with Multimodal Information Zhou Yu
9 Jul, 2:05 PM-2:15 PM Live QA Zhou Yu
9 Jul, 2:15 PM-2:50 PM Dungeons and DQNs: Grounding Language in Shared Experience Mark Riedl
9 Jul, 2:50 PM-3:00 PM Live QA Mark Riedl
9 Jul, 3:00 PM-3:15 PM REVERIE Challenge Yuankai Qi
9 Jul, 3:15 PM-3:35 PM REVERIE Challenge Talk REVERIE Challenge Winners
9 Jul, 3:35 PM-3:45 PM REVIERE Live QA REVERIE Challenge Winners
9 Jul, 4:00 PM-4:35 PM Vision+Language Research: Self-supervised Learning, Adversarial Training, Multimodal Inference and Explainability Jingjing (JJ) Liu
9 Jul, 4:35 PM-4:45 PM Live QA Jingjing (JJ) Liu
9 Jul, 4:45 PM-4:50 PM On the role of effective and Referring questions in GuessWhat!? Mauricio Mazuecos
9 Jul, 4:50 PM-4:55 PM Extending ImageNet to Arabic using Arabic WordNet Extending ImageNet to Arabic using Arabic WordNet
9 Jul, 4:55 PM-5:00 PM Toward General Scene Graph: Integration of Visual Semantic Knowledge with Entity Synset Alignment Woo Suk Choi
9 Jul, 5:00 PM-5:05 PM Latent Alignment of Procedural Concepts in Multimodal Recipes Hossein Faghihi
9 Jul, 5:05 PM-5:10 PM Visual Question Generation from Radiology Images Mourad Sarrouti
9 Jul, 5:10 PM-5:45 PM Poster Session and QA All Participants
You can open the livestream video and in a separate window.

Pre-recorded Talks