All times Pacific Time
Speaker | Title | Time | Live Event |
---|---|---|---|
Gedas Bertasius |
Is Space-Time Attention All You Need for Video Understanding? | 8:00 - 8:30 AM | [Recording] [Slides] |
Jean-Baptiste Alayrac |
Towards Versatile and Powerful MultiModal Networks | 8:30 - 9:00 AM | [Recording] [Slides] |
Speaker | Title | Time | Live Event |
---|---|---|---|
Carl Vondrick |
Predicting Unpredictability | 3:00 - 3:30 PM | [Recording] [Slides] |
Huijuan Xu |
Toward Compositional Action Recognition Using Semantic Scene Graphs | 3:30 - 4:00 PM | [Recording] [Slides] |
Speaker | Session | Video Link | Q&A (June 19th) |
---|---|---|---|
|
ActivityNet Temporal Action Localization Results | YouTube BiliBili | N.A. |
|
ActivityNet Dense Event Captioning | YouTube BiliBili | N.A. |
|
ActivityNet Entities Object Localization | YouTube BiliBili | 11:00-11:30 AM |
|
HACS Temporal Action Localization Challenge 2021 | YouTube BiliBili | N.A. |
|
Kinetics-700 | YouTube BiliBili | N.A. |
|
AVA-Kinetics & Active Speakers | YouTube BiliBili | N.A. |
|
ActEV SDL Unknown Facility | YouTube BiliBili | 2:30-3:00 PM* |
|
TinyActions | YouTube BiliBili | N.A. |
|
SoccerNet Challenge | YouTube BiliBili | N.A. |
|
Video Semantic Role Labeling | YouTube BiliBili | N.A. |
|
MMAct Challnge | YouTube BiliBili | N.A. |
|
HOMAGE | YouTube BiliBili | N.A. |