USC researchers presented the latest developments in their work on topics such as AI-assisted fashion design, facial recognition, and AI-generated video and audio. Photo/iStock.
This June, USC researchers presented the latest developments in their work on topics such as AI-assisted fashion design, facial recognition, and AI-generated video and audio at the IEEE/CVF Computer Vision and Pattern Recognition (CVPR) Conference in New Orleans. The conference is one of the largest industry and academic gatherings on artificial intelligence, bringing in more than 180 organizations and 9,000 attendees.
Students and faculty from USC were featured in 12 papers, including collaborations with companies like Amazon and Microsoft, with nearly half of all attendees coming from the machine learning and artificial intelligence industry. The papers span a wide breadth of emergent topics in the field, from determining if facial appearance can be constructed from voice recordings to improving object detection in autonomous driving.
To learn more about USC at CVPR, details and paper links are below:
Efficient Video Instance Segmentation via Tracklet Query and Proposal
Jialian Wu (State University of New York at Buffalo)*; Sudhir Yarram (University at Buffalo); Hui Liang (Amazon); Tian Lan (Amazon Inc); Junsong Yuan (State University of New York at Buffalo, USA); Jayan Eledath (Amazon); Gerard Medioni (USC)
Toward Practical Self-Supervised Monocular Indoor Depth Estimation
Cho-Ying Wu (USC); Jialiang Wang (Facebook Inc.); Michael Hall (Facebook); Ulrich Neumann (USC); Shuochen Su (Facebook Inc.)
Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
Cho-Ying Wu (USC); Chin-Cheng Hsu (USC); Ulrich Neumann (USC)
Point-NeRF: Point-based Neural Radiance Fields
Qiangeng Xu (USC); Zexiang Xu (Adobe Research); Julien Philip (Adobe); Sai Bi (Adobe Research); Zhixin Shu (Adobe Research); Kalyan Sunkavalli (Adobe Research); Ulrich Neumann (USC)
Cross-Domain Adaptive Teacher for Object Detection
Yu-Jhe Li (Carnegie Mellon University); Xiaoliang Dai (Facebook); Chih-Yao Ma (Facebook); Yen-Cheng Liu (Georgia Institute of Technology); Kan Chen (USC); Bichen Wu (Facebook Research); Zijian He (Facebook); Kris Kitani (Carnegie Mellon University); Peter Vajda (Facebook)
CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields
Can Wang (City University of Hong Kong); Menglei Chai (Snap Inc.); Mingming He (USC ICT); Dongdong Chen (Microsoft Cloud AI); Jing Liao (City University of Hong Kong)
Exemplar-based Pattern Synthesis with Implicit Periodic Field Network
Haiwei Chen (USC); Jiayi Liu (USC); Weikai Chen (Tencent America); Shichen Liu (USC); Yajie Zhao (USC)
Tianye Li (USC); Miroslava Slavcheva (Reality Labs Research); Michael Zollhöfer (Facebook Reality Labs); Simon Green (Facebook Reality Labs); Christoph Lassner (Meta Reality Labs Research); Changil Kim (Facebook); Tanner Schmidt (Facebook Reality Labs); Steven Lovegrove (Facebook Reality Labs); Michael Goesele (Facebook Reality Labs); Richard Newcombe (Facebook); Zhaoyang Lv (Facebook)
Implicit Feature Decoupling with Depthwise Quantization
Iordanis Fostiropoulos (USC); Barry Boehm (USC)
Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving
Hanjiang Hu (Carnegie Mellon University); Zuxin Liu (Carnegie Mellon University); Sharad Chitlangia (Amazon); Akhil Agnihotri (USC); Ding Zhao (Carnegie Mellon University)
Failure Modes of Domain Generalization Algorithms
Tigran Galstyan (YerevaNN); Hrayr Harutyunyan (USC Information Sciences Institute); Hrant Khachatrian (YerevaNN); Greg Ver Steeg (USC Information Sciences Institute); Aram Galstyan (USC Information Sciences Institute)
FashionVLP: Vision Language Transformer for Fashion Retrieval with Feedback
Sonam Goenka (Amazon); Zhaoheng Zheng (USC); Ayush Jaiswal (Amazon.com Inc.); Rakesh Chada (Amazon); Yue Wu (Amazon.com Inc.); Varsha Hedau (Amazon); Pradeep Natarajan (Amazon.com Inc.)
Published on July 8th, 2022
Last updated on May 16th, 2024
