曹原周汉
博士、副教授
博士、副教授
办公电话: | 电子邮件: yzhcao@bjtu.edu.cn |
通讯地址: | 邮编: |
2013-09 至 2017-09,澳大利亚阿德莱德大学,计算机科学技术,博士,导师:沈春华
2010-09 至 2013-06,四川大学,模式识别与智能系统,硕士,导师:滕奇志
2006-09 至 2010-06,西南民族大学,自动化,学士
2023-01 至 今,北京交通大学,计算机与信息技术学院,副教授
2020-06 至 2022-12,北京交通大学,计算机与信息技术学院,讲师
2019-01 至 2020-01, 澳大利亚阿德莱德大学,计算机科学学院,讲师
2017-11 至 2018-12, 瑞士IDIAP研究所,博士后
计算机视觉、深度学习、自动驾驶
2025级硕士招生名额已满
主持项目:
参与项目:
本科生课程:
《数据结构与算法》
研究生课程:
《机器视觉基础》
2024:
1. Yutong Gao; Congyan Lang; Fayao Liu; Chuan-Sheng Foo; Yuanzhouhan Cao; Lijuan Sun; Yunchao Wei, Mining Semantic Correlations Between Mispredictions and Corrections for Interactive Semantic Segmentation, IEEE Trans., on Neural Net., and Learn. Sys., 2024. (CCF B).
2. Hui Zhang; Guiyang Luo; Yuanzhouhan Cao; Xiao Wang; Yidong Li; Fei-Yue Wang, Scale-Disentangled and Uncertainty-Guided Alignment for Domain-Adaptive Object Detection, IEEE Trans. on Intell. Transp. Sys., 2024. (CCF B, 交通领域顶刊).
3. Zhenguo Zhang; Yuanzhouhan Cao; Hui Zhang; Naiyue Chen; Chao Ren; Yidong Li. Vision BEV-MAE: Masked Bird’s Eye View Autoencoders for Camera-based 3D Object Detection, China Automation Congress, 2024.
2023:
1. Luxin Cai; Naiyue Chen; Yuanzhouhan Cao; Jihuan He; Yidong Li, FedCE: Personalized Federated Learning Method based on Clustering Ensembles, ACM Multim., 2023. (CCF A).
2. Zisong Chen; Chunyu Lin; Lang Nie; Zhijie Shen; Kang Liao; Yuanzhouhan Cao; Yao Zhao, S-OmniMVS: Incorporating Sphere Geometry into Omnidirectional Stereo Matching, ACM Multim., 2023. (CCF A).
3. Yizhong Pan; Xiao Liu; Xiangyu Liao; Yuanzhouhan Cao; Chao Ren, Random Sub-Samples Generation for Self-Supervised Real Image Denoising, IEEE Inter. Conf. on Comp. Vis., 2023. (CCF A).
4. Yutong Gao; Congyan Lang; Fayao Liu; Yuanzhouhan Cao; Lijuan Sun; Yunchao Wei, Dynamic Interaction Dilation for Interactive Human Parsing, IEEE Trans. on Multim., 2023. (CCF B).
5. Yuanzhouhan Cao; Hui Zhang; Yidong Li; Congyan Lang; Tao Wang, Learning Instance Geometry Graph for Monocular 3D Object Detection, IEEE Smart World Cong., 2023. (Oral Presentation).
2022:
1. Yuanzhouhan Cao; Hui Zhang; Yidong Li; Chao Ren; Congyan Lang; CMAN: Leaning Global Structure Correlation for Monocular 3D Object Detection, IEEE Trans. on Intell. Transp. Sys., 2022. (CCF B, 交通领域顶刊).
2. Huifang Li; Yidong Li; Yuanzhouhan Cao; Yushan Han; Yi Jin; Yunchao Wei; Weakly Supervised Object Detection with Class Prototypical Network, IEEE Trans. on Multim., 2022. (CCF B).
2021:
1. Yuanzhouhan Cao; Yidong Li; Haokui Zhang; Chao Ren; Yifan Liu; Learning Structure Affinity for Video Depth Estimation, ACM Multim., 2021. (CCF A, Oral Presentation).
2. Chao Ren; Xiaohai He; Linbo Qing; Yuanzhouhan Cao; Deep Deblocker Driven Adaptive Iteration Scheme for Compressed Image Recovery. IEEE Inter. Conf. on Multim. Expo, 2021. (CCF B).
3. Yidong Li; Wenhua Liu; Yi Jin; Yuanzhouhan Cao; SPGAN: Face Forgery Using Spoofing Generative Adversarial Networks, ACM Trans. on Multim. Comp. Commu. Appl., 2021. (CCF B).
Before 2020:
1. Haokui Zhang; Chunhua Shen;Ying Li; Yuanzhouhan Cao; Yu Liu; Youliang Yan; Exploiting Temporal Consistency for Real-Time Video Depth Estimation, IEEE Inter. Conf. on Comp. Vis., 2019. (CCF A).
2. Yuanzhouhan Cao; Tianqi Zhao; Ke Xian; Chunhua Shen; Zhiguo Cao; Shugong Xu; Monocular Depth Estimation With Augmented Ordinal Depth Relationships, IEEE Trans. on Image Proc., 2018. (CCF A).
3. Yuanzhouhan Cao; Olivier Canévet; Jean-Marc Odobez; Leveraging Convolutional Pose Machine s for Fast and Accurate Head Pose Estimation, IEEE/RSJ Inter. Conf. on Intell. Rob. and Syst., 2018. (CCF C, Spotlight Presentation).
4. Yuanzhouhan Cao; Zifeng Wu; Chunhua Shen; Estimating Depth From Monocular Images as Class ification Using Deep Fully Convolutional Residual Networks, IEEE Trans. on Circ. Sys. Vid. Tech., 2017. (CCF B,ESI高被引).
5. Peng Wang#; Yuanzhouhan Cao#; Chunhua Shen; Lingqiao Liu; Heng Tao Shen; Temporal Pyramid Pooling-Based Convolutional Neural Network for Action Recognition. IEEE Trans. on Circ. Sys. Vid. Tech., 2017. (CCF B, #共同第一作者).
6. Yuanzhouhan Cao; Chunhua Shen; Heng Tao Shen; Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation, IEEE Trans. on Image Proc., 2016. (CCF A).
1. 一种基于移动终端的物体三维重建方法, 第一发明人
2. 一种基于实例结构相关性的二维图像中三维目标检测方法,第一发明人
3. 基于多层级跨模态自注意力机制的三维目标检测方法,第一发明人
CCF多媒体技术专业委员会 执行委员
CCF计算机视觉专委会 委员
CCF人工智能与模式识别专委会 委员