USC Researchers Present 16 Papers at CVPR

USC researchers are presenting 16 papers this week at the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, the premiere venue for the latest findings in computer vision. Topics covered by USC researchers include vision-and-language navigation, 3D human reconstruction, representation learning and batch model consolidation.

Accepted papers (USC-affiliated authors in bold):

Decentralized Learning With Multi-Headed Distillation Poster Session TUE-PM

Andrey Zhmoginov (Google) · Mark Sandler (Google) · Nolan Miller (University of Southern California) · Gus Kristiansen (Google) · Max Vladymyrov (Google)

The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning Poster Session TUE-AM

Joshua C. Zhao (Purdue University) · Ahmed Roushdy Elkordy (University of Southern California) · Atul Sharma (Purdue University) · Yahya H. Ezzeldin (University of Southern California) · Salman Avestimehr (University of Southern California) · Saurabh Bagchi (KeyByte LLC)

A Meta-Learning Approach to Predicting Performance and Data Requirements Poster Session TUE-AM

Achin Jain (Amazon) · Gurumurthy Swaminathan (Amazon) · Paolo Favaro (Institute für Informatik, University of Bern) · Hao Yang (Amazon) · Avinash Ravichandran (Cruise) · Hrayr Harutyunyan (University of Southern California) · Alessandro Achille (California Institute of Technology) · Onkar Dabeer (Amazon) · Bernt Schiele (Max Planck Institute for Informatics) · Ashwin Swaminathan (University of Maryland, College Park) · Stefano Soatto (AWS)

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction Poster Session TUE-AM

Zhen Wang (University of California, Los Angeles) · Shijie Zhou (University of California, Los Angeles) · Jeong Joon Park (Stanford University) · Despoina Paschalidou (Stanford) · Suya You (University of Southern California) · Gordon Wetzstein (Stanford University) · Leonidas Guibas (Stanford University) · Achuta Kadambi (UCLA)

SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers Poster Session WED-AM

Defu Cao (University of Southern California) · Zhaowen Wang (Adobe Research) · Jose Echevarria (Adobe Research) · Yan Liu (University of Southern California)

Improving Zero-Shot Generalization and Robustness of Multi-Modal Models Poster Session WED-AM

Yunhao Ge (University of Southern California) · Jie Ren (Google) · Andrew Gallagher (Google) · Yuxiao Wang (Google) · Ming-Hsuan Yang (University of California at Merced) · Hartwig Adam (Google Research) · Laurent Itti (USC) · Balaji Lakshminarayanan (Google Brain) · Jiaping Zhao (Google)

CUDA: Convolution-Based Unlearnable Datasets Poster Session TUE-AM

Vinu Sankar Sadasivan (University of Maryland College Park) · Mahdi Soltanolkotabi (University of Southern California) · Soheil Feizi (University of Maryland, College Park)

TBP-Former: Learning Temporal Bird’s-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving Poster Session TUE-AM

Shaoheng Fang (None) · Zi Wang (Shanghai Jiaotong University) · Yiqi Zhong (University of Southern California) · Junhao Ge (Shanghai Jiaotong University) · Siheng Chen (Shanghai Jiao Tong University)

STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition Poster Session TUE-AM

Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos Poster Session THU-AM

Ziqian Bai (Simon Fraser University & Google) · Feitong Tan (Google) · Zeng Huang (University of Southern California) · Kripasindhu Sarkar (Google) · Danhang Tang (Google Inc.) · Di Qiu (Google) · Abhimitra Meka (Google) · Ruofei Du (Google) · Mingsong Dou (Google) · Sergio Orts-Escolano (Google) · Rohit Pandey (Google) · Ping Tan (Alibaba DAMO academy) · Thabo Beeler (Google) · Sean Fanello (Google) · Yinda Zhang (Google)

Complete 3D Human Reconstruction From a Single Incomplete Image Poster Session WED-AM

Junying Wang (None) · Jae Shin Yoon (Adobe Systems) · Tuanfeng Y. Wang (None) · Krishna Kumar Singh (Adobe Systems) · Ulrich Neumann (University of Southern California)

Batch Model Consolidation: A Multi-Task Model Consolidation Framework Poster Session TUE-AM

Iordanis Fostiropoulos (University of Southern California) · Jiaye Zhu (University of Southern California) · Laurent Itti (University of Southern California)

Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning Poster Session WED-PM

Zhuowan Li (Johns Hopkins University) · Xingrui Wang (University of Southern California) · Elias Stengel-Eskin (Johns Hopkins University) · Adam Kortylewski · Wufei Ma (Johns Hopkins University) · Benjamin Van Durme (Johns Hopkins University) · Alan L. Yuille (Johns Hopkins University)

Mobile User Interface Element Detection via Adaptively Prompt Tuning Poster Session WED-AM

Zhangxuan Gu (None) · Zhuoer Xu (Nanjing University) · Haoxing Chen (Nanjing University) · Jun Lan (Shanghai Jiaotong University) · Changhua Meng (Nanjing University) · Weiqiang Wang (University of Southern California)

Biomechanics-Guided Facial Action Unit Detection Through Force Modeling Poster Session WED-AM

Zijun Cui (University of Southern California) · Chenyi Kuang (Rensselaer Polytechnic Institute) · Tian Gao (International Business Machines) · Kartik Talamadupula (IBM Research) · Qiang Ji (Rensselaer Polytechnic Institute)

Iterative Vision-and-Language Navigation Poster Session WED-PM

Jacob Krantz (Oregon State University) · Shurjo Banerjee (University of Michigan) · Wang Zhu (University of Southern California) · Jason Corso (University of Michigan) · Peter Anderson (Google) · Stefan Lee (Oregon State University) · Jesse Thomason (University of Southern California)

Published on June 21st, 2023

Last updated on May 16th, 2024