Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Xing, Tengfei"'
Autor:
Yang, Zhongyu, Liu, Mai, Xie, Jinluo, Zhang, Yueming, Shen, Chen, Shao, Wei, Jiao, Jichao, Xing, Tengfei, Hu, Runbo, Xu, Pengfei
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 images and standard-definition (SD) maps to explore the boundaries of
Externí odkaz:
http://arxiv.org/abs/2406.10125
Autor:
Yang, Zhongyu, Shen, Chen, Shao, Wei, Xing, Tengfei, Hu, Runbo, Xu, Pengfei, Chai, Hua, Xue, Ruini
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 and crucial for automated driving. Moreover, current lane representation
Externí odkaz:
http://arxiv.org/abs/2403.14354
Autor:
Yang, Zhongyu, Shen, Chen, Shao, Wei, Xing, Tengfei, Hu, Runbo, Xu, Pengfei, Chai, Hua, Xue, Ruini
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 with corner lanes well. To address this problem, this paper proposes a n
Externí odkaz:
http://arxiv.org/abs/2304.11546
Autor:
Zhang, Yueming, Yao, Xingxu, Liu, Chao, Chen, Feng, Song, Xiaolin, Xing, Tengfei, Hu, Runbo, Chai, Hua, Xu, Pengfei, Zhang, Guoshan
Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting high-quality
Externí odkaz:
http://arxiv.org/abs/2204.04492
Publikováno v:
In Journal of Alloys and Compounds 5 November 2024 1004
Autor:
Liao, Haojin, Song, Xiaolin, Zhao, Sicheng, Zhang, Shanghang, Yue, Xiangyu, Yao, Xingxu, Zhang, Yueming, Xing, Tengfei, Xu, Pengfei, Wang, Qiang
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 between the source and target domains. In this report, we introduce a u
Externí odkaz:
http://arxiv.org/abs/2110.14240
Autor:
Zhang, Yueming, Song, Xiaolin, Bai, Bing, Xing, Tengfei, Liu, Chao, Gao, Xin, Wang, Zhihui, Wen, Yawei, Liao, Haojin, Zhang, Guoshan, Xu, Pengfei
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-time running brings new challenges for convolutional network models. In
Externí odkaz:
http://arxiv.org/abs/2106.08713
Autor:
Zhao, Sicheng, Ma, Yunsheng, Gu, Yang, Yang, Jufeng, Xing, Tengfei, Xu, Pengfei, Hu, Runbo, Chai, Hua, Keutzer, Kurt
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. extracting visual and/or audio features and training classifiers. In this pa
Externí odkaz:
http://arxiv.org/abs/2003.00832
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.