From June 19th through 24th some of the top researchers working in computer vision will gather in-person and virtually for IEEE/CVF’s annual international conference on Computer Vision and Pattern Recognition (CVPR). This hybrid conference will include talks, workshops, short courses, and an expo, making it the perfect setting for academics, students, and industry representatives to share innovative information and make high quality connections.
CAIDA has 7 members who have had a total of 9 papers accepted for CVPR 2022. An additional 9 UBC researchers have had papers accepted for CVPR this year, totalling a representation of 16 individuals from UBC across 11 different papers. This is an extraordinary accomplishment and each researcher deserves a huge congratulation. You can see a list of our members’ papers below, followed by all accepted papers represented by UBC members that do not feature CAIDA members. A full list of CVPR 2022 accepted papers can be found here, and you can learn more about this year’s conference here.
Accepted Papers Featuring CAIDA Members:
Nourhan Bayasi (University of British Columbia )*; Ghassan Hamarneh (Simon Fraser University); Rafeef Garbi (University of British Columbia)
BoosterNet: Improving Domain Generalization of Deep Neural Nets using Culpability-Ranked Features
Mohsen Gholami (University of British Columbia)*; Bastian Wandt (University of British Columbia); Helge Rhodin (UBC); Rabab Ward (University of British Columbia); Z. Jane Wang (University of British Columbia)
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation
Klaus Greff (Google)*; Francois W Belletti (Google); Lucas Beyer (Google Brain); Carl Doersch (DeepMind); Yilun Du (MIT); Daniel Duckworth (Google); David J Fleet (University of Toronto); Danushen L Gnanapragasam (Google Inc); Florian Golemo (Mila, ElementAI); Charles Herrmann (Google); Thomas Kipf (Google Brain); Abhijit Kundu (Google); Dmitry Lagun (Google); Issam Hadj Laradji (ServiceNow); Hsueh-Ti Liu (University of Toronto); Henning Meyer (Google); Yishu Miao (Haiper Ltd); Derek Nowrouzezahrai (McGill University); A. Cengiz Oztireli (University of Cambridge, Google); Etienne Pot (Google); Noha Radwan (Google); Daniel Rebain (Google Inc.); Sara Sabour (Google); Mehdi S. M. Sajjadi (Google Brain); Matan Sela (Google); Vincent Sitzmann (Massachusetts Institute of Technology); Austin C Stone (Google); Deqing Sun (Google); Suhani Vora (Google ); Ziyu Wang (Haiper Ltd); Tianhao Wu (University of Cambridge); Kwang Moo Yi (University of British Columbia); Fangcheng Zhong (University of Cambridge); Andrea Tagliasacchi (Google Brain and University of Toronto)
Kubric: A scalable dataset generator
Xingzhe He (University of British Columbia)*; Bastian Wandt (University of British Columbia); Helge Rhodin (UBC)
GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation
Kacper Kania (Warsaw University of Technology)*; Kwang Moo Yi (University of British Columbia); Marek A Kowalski (Microsoft); Tomasz Trzcinski (Tooploox, Warsaw University of Technology, Jagiellonian University of Cracow); Andrea Tagliasacchi (Google Brain and University of Toronto)
CoNeRF: Controllable Neural Radiance Fields
Daniel Rebain (Google Inc.)*; Mark J Matthews (Google Inc.); Kwang Moo Yi (University of British Columbia); Andrea Tagliasacchi (Google Brain and University of Toronto); Dmitry Lagun (Google)
LOLNerf: Learn from One Look
Mohammed Suhail (University of British Columbia)*; Carlos Esteves (Google Research); Leonid Sigal (University of British Columbia); Ameesh Makadia (Google Research)
Light Field Neural Rendering
Tianxin Tao (University of British Columbia)*; Xiaohang Zhan (The Chinese University of Hong Kong); Zhongquan Chen (University of California, Davis); Michiel van de Panne (University of British Columbia)
Style-ERD: Responsive and Coherent Online Motion Style Transfer
Bastian Wandt (University of British Columbia)*; Jim Little (University of British Columbia, Canada); Helge Rhodin (UBC)
ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses
Accepted Papers from non-CAIDA UBC Researchers:
Guande Wu (New York University)*; jianzhe peter lin (University of British Columbia); Claudio Silva (NYU)
IntentVizor: Towards Generic Query Guided Interactive Video Summarization
Qi Yan (UBC)*; Jianhao Zheng (EPFL); Simon A Reding (EPFL); Shanci Li (EPFL); Iordan Doytchinov (EPFL)
CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data
Note: All CAIDA Members have been bolded and a link has been provided to their personal webpages