80 citations · 235 across the 18 of their papers we have counts for
19 papers
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…
More is Better: Deep Domain Adaptation with Multiple Sources
Sicheng Zhao, Hui Chen, Hu Huang +2
In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the l…
LDTR: Transformer-based Lane Detection with Anchor-chain Representation
Zhongyu Yang, Chen Shen, Wei Shao +5
Despite recent advances in lane detection methods, scenarios with limited- or no-visual-clue of lanes due to factors such as lighting conditions and occlusion remain challenging an…
CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection
Zhongyu Yang, Chen Shen, Wei Shao +5
Lane detection is challenging due to the complicated on road scenarios and line deformation from different camera perspectives. Lots of solutions were proposed, but can not deal wi…
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…
3rd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition
Haojin Liao, Xiaolin Song, Sicheng Zhao +7
The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance b…
Multi-Source Domain Adaptation for Object Detection
Xingxu Yao, Sicheng Zhao, Pengfei Xu +1
To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unl…
2nd Place Solution for Waymo Open Dataset Challenge -- Real-time 2D Object Detection
Yueming Zhang, Xiaolin Song, Bing Bai +8
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images. Besides the high accuracy of the prediction, the requirement of real-t…
Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
Sicheng Zhao, Xuanbai Chen, Xiangyu Yue +7
Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of d…
Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
Sicheng Zhao, Yang Xiao, Jiang Guo +5
Sentiment analysis of user-generated reviews or comments on products and services in social networks can help enterprises to analyze the feedback from customers and take correspond…
ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation
Sicheng Zhao, Yezhen Wang, Bo Li +5
Due to its robust and precise distance measurements, LiDAR plays an important role in scene understanding for autonomous driving. Training deep neural networks (DNNs) on LiDAR data…
Emotion-Based End-to-End Matching Between Image and Music in Valence-Arousal Space
Sicheng Zhao, Yaxian Li, Xingxu Yao +4
Both images and music can convey rich semantics and are widely used to induce specific emotions. Matching images and music with similar emotions might help to make emotion percepti…
Rethinking Distributional Matching Based Domain Adaptation
Bo Li, Yezhen Wang, Tong Che +6
Domain adaptation (DA) is a technique that transfers predictive models trained on a labeled source domain to an unlabeled target domain, with the core difficulty of resolving distr…
Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Sicheng Zhao, Bo Li, Colorado Reed +2
In many practical applications, it is often difficult and expensive to obtain enough large-scale labeled data to train deep neural networks to their full capability. Therefore, tra…
MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
Sicheng Zhao, Bo Li, Xiangyu Yue +2
Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Since the…
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…
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…