姜晓燕，计算机系副教授、硕导；耶拿大学（德国）计算机科学博士。研究方向：计算机视觉、机器学习；研究课题：多目标检测与跟踪、视觉SLAM、语义分割、姿态估计。Applied Intelligence 期刊副主编（SCI, IF: 5.3）。曾获德国 DAAD、国家留学基金委CSC奖学金资助。

已发表论文50 余篇，包括Tran. SMC, Pattern Recognition, Trans. ITS、KBS、SPIC、EAAI、ICME、ICIP等领域顶级期刊和会议；国际会议 ICPCSEE2019 的PC、国际会议CVIP 2024、HCIVR 2024的TPC。国际会议 ICFTIC2019、IWITC2021、CISE2023作主旨报告；为多个顶级期刊与国际会议的评审等。作为主要参与人获得上海市科技进步奖二等奖。申请发明专利 8 项（实审），已授权2项，授权实用新型专利 5 项。

主持/参与国家自然科学基金青年项目、重点项目、面上项目、上海市科委重点项目多项；负责和参与人工智能相关横向项目多项，应用领域广泛，包括机器视觉、视频监控、缺陷检测、道路巡检、智慧医疗等。现为电子与电气工程学院多维度人工智能科研团队负责人。

每年招收3-5名研究生，团队以学生发展为中心，打牢从传统视觉算法到深度学习及大模型相关的关键知识与理论，结合实际场景，培养独立思考，发现问题和解决问题的能力。目标为激发大家持续终身学习的内驱力！

主要成果：

[J1] TV-Net: A Structure-level Feature Fusion Network based on Tensor Voting for Road Crack Segmentation. W. Zheng, X. Jiang*#, Z. Fang, and Y. Gao. IEEE Transactions on Intelligent Transportation Systems (TITS), Impact Factor: 8.5, pp.:1-12,2024

[J2] A Multi-Scale Coarse-to-Fine Human Pose Estimation Network with Hard Keypoint Mining. X. Jiang, H. Tao, J. Hwang, and Z. Fang. IEEE Transactions on Systems, Man and Cybernetics: Systems (TSMC), Impact Factor: 8.7. pp.: 1730-1741, 2023.3

[J3] An Automatic Prompt Generation for Specific Classes based on Visual Language Pre-training Models. B. Han, X. Jiang*, Z. Fang, H. Fujita, and Y. Gao. Pattern Recognition. pp.: 1-11, IF: 8, 2023

[J4] A Sparse Graph Wavelet Convolution Neural Network for Video-based Person Re-identification. Y. Yao, X. Jiang*, H. Fujita, and Z. Fang. Pattern Recognition, Impact factor: 8, Vol: 129, pp.: 1-12, 2022

[J5] Effective Person Re-identification by Self-Attention Model Guided Feature Learning. Y. Li, X. Jiang#*, and J. Hwang. Knowledge-Based Systems, Impact factor: 8.8, Vol: 187, 2020

[J6] Multi-Marker Tracking for Large-scale X-ray Stereo Video Data. X. Jiang, M. Simon, Y. Yang, and J. Denzler. Signal Processing: Image Communication. 59(2017): 140-149, 2017

[J7] Photometric Transfer for Direct Visual Odometry. K. Zhu, X. Jiang*, Z. Fang, Y. Gao, H. Fujita, and J. Hwang. Knowledge-Based Systems. IF: 8.8, Vol: 213, 2021

[C1] LiDUT-Depth: A Lightweight Self-supervised Depth Estimation Model featuring Dynamic. Upsampling and Triplet Loss Optimization. Hao Jiang, Xuan Shao, Zhijun Fang, and Xiaoyan Jiang. ICPR2024

[C2] Depth Estimation of Multi-modal Scene based on Multi-scale Modulation. A. Wang, Z. Fang, X. Jiang, Y. Gao, C. Shao, G. Cao, and S. Ma. IEEE International Conference on Image Processing (ICIP), London, UK, 2023.

[C3] Unsupervised learning of depth and ego-motion with spatial-temporal geometric constraints. A. Wang, Y. Gao, Z. Fang*, X. Jiang*, S. Wang, S. Ma, and J. Hwang. International Conference on Multimedia and Expo (ICME), Shanghai China. 2019