no code implementations • 18 Apr 2024 • Xiao Wang, Ke Tang, Xingyuan Dai, Jintao Xu, Quancheng Du, Rui Ai, Yuxiao Wang, Weihao Gu
To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S4TP) framework.
no code implementations • 12 Mar 2024 • Weiying Xue, Qi Liu, Qiwei Xiong, Yuxiao Wang, Zhenao Wei, Xiaofen Xing, Xiangmin Xu
Human-object interaction (HOI) detection aims to locate human-object pairs and identify their interaction categories in images.
no code implementations • 4 Mar 2024 • Yuxiao Wang, Zhenao Wei, Xinyu Jiang, Yu Lei, Weiying Xue, Jinxiu Liu, Qi Liu
Recent human-object interaction (HOI) detection approaches rely on high cost of manpower and require comprehensive annotated image datasets.
no code implementations • 23 Jan 2024 • Shaoheng Fang, Rui Ye, Wenhao Wang, Zuhong Liu, Yuxiao Wang, Yafei Wang, Siheng Chen, Yanfeng Wang
In this paper, we introduce FedRSU, an innovative federated learning framework for self-supervised scene flow estimation.
1 code implementation • CVPR 2023 • Yunhao Ge, Jie Ren, Andrew Gallagher, Yuxiao Wang, Ming-Hsuan Yang, Hartwig Adam, Laurent Itti, Balaji Lakshminarayanan, Jiaping Zhao
We also show that our method improves across ImageNet shifted datasets, four other datasets, and other model architectures such as LiT.
1 code implementation • CVPR 2023 • Zheng Xu, Maxwell Collins, Yuxiao Wang, Liviu Panait, Sewoong Oh, Sean Augenstein, Ting Liu, Florian Schroff, H. Brendan McMahan
Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past.
1 code implementation • CVPR 2021 • Long Zhao, Yuxiao Wang, Jiaping Zhao, Liangzhe Yuan, Jennifer J. Sun, Florian Schroff, Hartwig Adam, Xi Peng, Dimitris Metaxas, Ting Liu
To evaluate the power of the learned representations, in addition to the conventional fully-supervised action recognition settings, we introduce a novel task called single-shot cross-view action recognition.
2 code implementations • 23 Oct 2020 • Ting Liu, Jennifer J. Sun, Long Zhao, Jiaping Zhao, Liangzhe Yuan, Yuxiao Wang, Liang-Chieh Chen, Florian Schroff, Hartwig Adam
Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people.