研究团队

赵旭

个人简介

上海交通大学教授，博士生导师。主要研究领域是计算机视觉、模式识别与机器学习、视频与多媒体分析等。2011年获上海交通大学模式识别与智能系统专业博士学位。曾在美国伊利诺伊大学香槟分校（UIUC）贝克曼研究所进行访学研究，在美国纽约州立大学布法罗分校和美国东北大学从事博士后研究工作，于2013年进入上海交通大学自动化系任教。长期开展“以人为中心的视觉计算”方向的研究工作，近年来发表论文100多篇，论文获IEEE 信号处理学会最佳论文奖、亚洲计算机视觉大会（ACCV）最佳论文提名奖、中国图象图形学学会会议最佳论文奖等奖项。指导学生多次获各类国际、国内科研竞赛冠军。是中国计算机学会多媒体专委会执行委员、中国图象图形学会多媒体专委会委员。曾任上海交通大学医疗机器人研究院院长助理，目前担任上海市医疗机器人技术创新中心副主任。

科研方向

“看人看物看世界，知象知义知因果”，让计算机通过视觉信息捕捉微妙复杂的变化，去感知、理解和重构三维世界，是实验室长期致力的研究目标。“以人为中心的视觉计算”包括下列细分研究方向：人体姿态估计、人体表面重建、视频行为理解、动态环境感知、医学影像分析、视觉检测测量等。相关方法和技术已应用于：自动驾驶、智能诊疗、智能工厂等新一代人工智能示范应用场景。

科研项目

近年部分科研项目：

主持，视频人体运动的层级时空模式表示与识别（国家自然科学基金面上项目，在研）
主持，视觉人体运动的贝叶斯学习、分析与合成（国家自然科学基金面上项目，结题）
主持，人体运动视觉分析中的动态隐结构模型研究（国家自然科学基金面上项目，结题）
主持，视频人体行为分析技术（企业合作-华为，结题）
主持，VRU意图识别和预测技术合作项目（企业合作-华为，结题）
主持，构建基于数据驱动的Halide性能方案技术（企业合作-华为，结题）
主持，基于深度学习的视觉检测算法研究（企业合作-华为，结题）
主持，Urban Maneuver Research（企业合作-宝马中国，结题）
主持，Machine Learning Based Environment Perception Research for Autonomous Driving（企业合作-宝马中国，结题）
参与，基于语义点云的智能汽车环境感知与建模（国家自然科学基金重点项目，骨干，结题）
主持，面向帕金森病早期诊断的多模态细粒度智能评估（“交大之星”（STAR）计划重点项目，在研）
参与，儿童先天性心脏病个体精准化智能诊疗系统研发（“交大之星”（STAR）计划重大项目，骨干，在研）

发表论文

部分代表性论文

[1] Z. Zhao, D. Wang, and X. Zhao*, “Movement Enhancement toward Multi-Scale Video Feature Representation for Temporal Action Detection,” in ICCV 2023.
[2] X. Wan, Z. Chen, and X. Zhao*, “View Consistency Aware Holistic Triangulation for 3D Human Pose Estimation,” Computer Vision and Image Understanding., 2023.
[3] Y. Deng, B. Li, Y. Yang, and X. Zhao*, “Temporally Consistent Reconstruction of 3D Clothed Human Surface with Warp Field,” Image Vision Computing, 2023.
[4] Y. Bao, X. Zhao*, and D. Qian*, “FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation,” IEEE Transactions Multimedia, 2023.
[5] Y. Ni and X. Zhao*, “3DTRIP: A General Framework for 3D Trajectory Recovery Integrated With Prediction,” IEEE Robotics and Automation Letters, 2023.
[6] Z. Chen, X. Zhao*, and X. Wan, “Structural Triangulation: A Closed-Form Solution to Constrained 3D Human Pose Estimation,” in ECCV, 2022.
[7] Y. Zhang, X. Zhao*, and D. Qian*, “Learning-Based Distortion Correction and Feature Detection for High Precision and Robust Camera Calibration,” IEEE Robotics and Automation Letters, 2022.
[8] H. Zhang, X. Zhao*, and D. Wang, “Semi-supervised Learning for Multi-label Video Action Detection,” in ACM International Conference on Multimedia. 2022.
[9] S. Zhang, X. Zhao*, and L. Fang, “CAT: Corner Aided Tracking With Deep Regression Network,” IEEE Transactions on Multimedia, 2021.
[10] H. Su, X. Zhao*, T. Lin, S. Liu, and Z. Hu, “Transferable Knowledge-Based Multi-Granularity Fusion Network for Weakly Supervised Temporal Action Detection,” IEEE Transactions on Multimedia, 2021.
[11] Z. Sui, Y. Zhou, X. Zhao*, A. Chen, and Y. Ni, “Joint Intention and Trajectory Prediction Based on Transformer,” in IROS, 2021.
[12] X. Song, X. Zhao*, L. Fang, H. Hu, and Y. Yu, “EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection,” International Journal of Computer Vision, 2020.
[13] T. Lin, X. Zhao*, and H. Su, “Joint Learning of Local and Global Context for Temporal Action Proposal Generation,” IEEE Transactions on Circuits System and Video Technology, 2020.
[14] Y. Qian, M. Yang, X. Zhao, C. Wang, and B. Wang, “Oriented Spatial Transformer Network for Pedestrian Detection Using Fish-Eye Camera,” IEEE Transactions on Multimedia, 2020.
[15] Z. Fan, X. Zhao*, T. Lin, and H. Su, “Attention-Based Multiview Re-Observation Fusion Network for Skeletal Action Recognition,” IEEE Transactions on Multimedia, 2019.
[16] X. Song, X. Zhao*, L. Fang, and T. Lin, “Discriminative representation combinations for accurate face spoofing detection,” Pattern Recognition, 2019.
[17] T. Lin, X. Zhao*, H. Su, C. Wang, and M. Yang, “BSN: Boundary Sensitive Network for Temporal Action Proposal Generation,” in ECCV, 2018.
[18] Y. Zou, X. Zhao*, and Y. Liu, “Measuring Crowd Collectiveness by Macroscopic and Microscopic Motion Consistencies,” IEEE Transactions on Multimedia, 2018.
[19] S. Zhang, X. Zhao*, L. Fang, H. Fei, and H. Song, “LED: Localization-Quality Estimation Embedded Detector,” in ICIP, 2018. (IEEE SPS Best Paper Award)
[20] X. Song, X. Zhao*, H. Hu, and L. Fang, “EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching,” in ACCV, 2018. (Best Paper Award Honorable Mention)
[21] T. Lin, X. Zhao*, and Z. Shou, “Single Shot Temporal Action Detection,” in ACM Multimedia 2017.
[22] L. Wang, X. Zhao*, Y. Si, L. Cao, and Y. Liu, “Context-Associative Hierarchical Memory Model for Human Activity Recognition and Prediction,” IEEE Transactions on Multimedia, 2017.
[23] X. Zhao, X. Li, Z. Wu, Y. Fu, and Y. Liu, “Multiple Subcategories Parts-Based Representation for One Sample Face Identification,” IEEE Transactions on Information Forensics and Security, 2013.
[24] X. Zhao, Y. Liu, and Y. Fu, “Exploring discriminative pose sub-patterns for effective action classification,” in ACM Multimedia, 2013.
[25] Z. Wu, X. Li, X. Zhao*, and Y. Liu*, “Hybrid generative-discriminative recognition of human action in 3D joint space,” in ACM Multimedia, 2012.
[26] X. Zhao, K.-H. Lin, Y. Fu, Y. Hu, Y. Liu, and T. S. Huang, “Text From Corners: A Novel Approach to Detect Text and Caption in Videos,” IEEE Transactions on Image Processing, 2011.
[27] X. Zhao, Y. Fu, and Y. Liu, “Human Motion Tracking by Temporal-Spatial Local Gaussian Process Experts,” IEEE Transactions on Image Processing, 2011.
[28] X. Zhao, Y. Fu, H. Ning, L. Yuncai, and T. S. Huang, “Human Pose Regression Through Multiview Visual Fusion,” IEEE Transactions on Circuits System and Video Technology, 2010.
[29] X. Li, X. Zhao*, Y. Fu, and Y. Liu, “Bimodal Gender Recognition from Face and Fingerprint,” in CVPR 2010.
[30] X. Zhao, and Y. Liu, “Generative tracking of 3D human motion by hierarchical annealed genetic algorithm,” Pattern Recognition, 2008.

获奖情况

2021，全国人工智能创新应用大赛一等奖（指导老师）

2020，MEDIA AI阿里巴巴文娱算法挑战赛冠军（指导老师）

2018，IEEE Signal Processing Society Conference Best Paper Award （Industry）

2018，ACCV 2018 Best Paper Award Honorable Mention

2018，ActivityNet-Large Scale Activity Recognition Challenge (CVPR)，Temporal Action Localization 单项冠军（指导老师）

2018，ActivityNet-Large Scale Activity Recognition Challenge (CVPR)，Temporal Action Proposals 单项亚军（指导老师）

2017，ActivityNet-Large Scale Activity Recognition Challenge (CVPR)，Temporal Action Localization 单项冠军（指导老师）

2017，ActivityNet-Large Scale Activity Recognition Challenge (CVPR)，Temporal Action Proposals 单项冠军（指导老师）

2017，第十届英特尔杯全国大学生软件创新大赛二等奖（优秀指导老师）

2014，上海市优秀博士论文奖

2014，第十七届全国图象图形学学术会议（NCIG2014）优秀论文奖

2012，上海交通大学优异学士论文奖（指导老师，与刘允才教授共同指导）

2011，AMD中国加速计算竞赛冠军（指导老师）

主讲课程

计算机视觉（AU7005，研究生课程，英文授课)

计算机视觉（AI4701，本科生课程，中文授课）

数字图像处理基础（AU3304 ，本科生课程，英文授课）