Publications (8)
Multi-source Distilling Domain Adaptation
Sicheng Zhao, Guangzhi Wang, Shanghang Zhang +7
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain…
Multi-source Domain Adaptation for Semantic Segmentation
Sicheng Zhao, Bo Li, Xiangyu Yue +5
Simulation-to-real domain adaptation for semantic segmentation has been actively studied for various applications such as autonomous driving. Existing methods mainly focus on a sin…
ROAM: Recurrently Optimizing Tracking Model
Tianyu Yang, Pengfei Xu, Runbo Hu +2
In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of t…
An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
Sicheng Zhao, Yunsheng Ma, Yang Gu +6
Emotion recognition in user-generated videos plays an important role in human-centered computing. Existing methods mainly employ traditional two-stage shallow pipeline, i.e. extrac…
MapVision: CVPR 2024 Autonomous Grand Challenge Mapless Driving Tech Report
Zhongyu Yang, Mai Liu, Jinluo Xie +7
Autonomous driving without high-definition (HD) maps demands a higher level of active scene understanding. In this competition, the organizers provided the multi-perspective camera…
S4OD: Semi-Supervised learning for Single-Stage Object Detection
Yueming Zhang, Xingxu Yao, Chao Liu +7
Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detect…