Overview

Most updated program available at the virtual site (https://events.rdmobile.com/Account/Login) and APP (download eventsential app and search for WACV).

 

Program Book:
https://drive.google.com/file/d/12KiaWtyATjm0BlQlJTB0krQr62vAiZsb/

WACV Program Overview
Main Conference	2023 January 4 – 6 (Wednesday - Friday)
Workshops and Tutorials	2023 January 3 and 7  (Tuesday & Saturday)

 

FG  Program Overview
Main Conference	2023 January 7 – 8 (Saturday - Sunday)
Workshops and Tutorials	2023 January 5 and 6  (Thursday & Friday)

 

Dinner provided on Wednesday, Thursday and full luau on Friday. Guest tickets can be purchased via the registration site.

 

Badge Pickup hours located outside of the Naupaka Ballroom

January 2    5 PM – 8 PM 
January 3    8 AM – 4 PM 
January 4    12 PM – 5 PM 
January 5    1 PM – 5 PM  (FG 8 AM – 9:30 AM)
January 6    1 PM – 5 PM (FG 8 AM – 9:30 AM)
January 7    8 AM – 5 PM
January 8    8 AM – 9:30 AM (FG)

 

** A bus schedule to/from the Courtyard Marriott will be posted soon.

 

Keynote Speakers

Bryan Catanzaro, Vice President, Applied Deep Learning, Nvidia

Kate Saenko, Professor Department of Computer Science, Boston University

Keynote                    Wednesday, January 4th                    5:00 PM HST

Bryan Catanzaro, Vice President of Applied Deep Learning Research at NVIDIA

Talk Title: Neural rendering: Computer Vision for post-Moore’s Law Graphics

Bryan Catanzaro is Vice President of Applied Deep Learning Research at NVIDIA, where he leads a team of AI researchers working on chip design, audio and speech, language modeling, graphics and vision, with the goal of finding practical new ways to use AI for NVIDIA’s products and workflows. DLSS, Megatron, CUDNN, Pascaline, WaveGlow and DeepSpeech are some of the projects he’s helped create. Bryan received his PhD in EECS from the University of California, Berkeley.

Keynote                    Thursday, January 5th                    5:00 PM HST

Kate Saenko, Professor Department of Computer Science, Boston University

Talk Title: Bridging the Domain Gap: Towards Robust and Generalizable Computer Vision

Kate Saenko is a Professor of Computer Science at Boston University where she leads the Computer Vision and Learning Group and is the founder and co-director of the Artificial Intelligence Research (AIR) initiative. She received a PhD from MIT EECS and did postdoctoral work at UC Berkeley and Harvard University. Her research interests are in AI and Computer Vision with a focus on efficient and robust representation learning. She is best known for her seminal work on domain adaptation and dataset bias, as well as early Vision & Language work on video captioning and visual question answering. Kate's service to the community includes organizing a long-running series of Visual Domain Adaptation (VisDA) competitions. Kate has served as an Associate Editor-in-Chief for PAMI and a Program Chair for CVPR 2020 and NeurIPS 2023. She has been appointed the Hariri Institute Data Science Faculty Fellow and received a Google Faculty Research Award.