Name：Xu Haixia
Title：Associate Professor
Type of tutor：Master's supervisor
Email：xuhaixia@email.tjut.edu.cn
Address：7-317A
I am currently an associate professor and master supervisor at School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China. I received my BS, MS, and PhD degrees from Northwestern Polytechnical University, Xian, China, in 2003, 2006, and 2009, respectively.
Computer Vision
Image/video processing
Remote sensing image processing
Statistical information processing
1. Research on Robust SAR Image Registration Methods Based on Graph Theory, National Natural Science Foundation of China, 2012.01-2014.12.
2. Research on Three-Dimensional Reconstruction of Large-Scale SAR Images Based on Compressive Sensing, National Natural Science Foundation of China, 2015.01-2018.12.
3. Research on 3D Reconstruction Model and Algorithm of Urban Targets in SAR Remote Sensing Images, Tianjin Natural Science Foundation, 2012.04-2015.03.
4. Online electronic examination system, horizontal project, 2014.05-2014.08.
5. Development and application of a 24-item unmanned intelligent examination multimodal large model for practicing physicians, horizontal project, 2025.11-2026.10.
[1] Haobo Fang, Haixia Xu, Xianbin Wen. EL-YOLO: an efficient and light YOLO algorithm for small object SAR ship detection, Journal of Applied Remote Sensing. 2025, 19(3), 036504.
[2] Wentao Li, Xinyu Wang, Haixia Xu, Liming Yuan, Furong Shi, Xianbin Wen, Jiao Liu. PLDF-S3: pseudo-label-driven framework for offshore to inshore unsupervised SAR image ship segmentation, IEEE Geoscience and remote sensing letters, 2025, 22, 4011505.
[3] Wei Dai, Haixia Xu, Furong Shi, Liming Yuan, Xinyu Wang, Xianbin Wen. ACDR-CRAFF: a multi-scale network based on adaptive channel and coordinate relational attention network for remote sensing scene classification, IET Image processing, 2025, 19(1), e70112.
[4] Wentao Li, Haixia Xu, Furong Shi, Liming Yuan, Xianbin Wen. Self-supervised network for oriented synthetic aperture radar ship detection based on self-distillation, Journal of Applied Remote Sensing. 2024, 18(4), 046504.
[5] Xinyu Wang, Furong Shi, Haixia Xu, Liming Yuan, Xianbin Wen. Dynamic convolution covariance network using multiscale feature fusion for remote sensing scene image classification, IEEE Journal of Selected Topics in Applied earth Observations and Remote Sensing. 2024, 17, 16815-16830.
[6] Xinyu Wang, Haixia Xu, Furong Shi, Liming Yuan, Xianbin Wen. Multiscale attention-based subdomain dynamic adaptation for cross-domain scene classification, IEEE Geoscience and Remote Sensing Letters. 2024, 21, 6004605.
[7] Xinyu Wang, Haixia Xu, Liming Yuan, Xianbin Wen. A lightweight and stochastic depth residual attention network for remote sensing scene classification, IET Image Processing. 2023, 17(11), 3106-3126.
[8] Kun Sun, Haixia Xu, Liming Yuan, Xianbin Wen. A tiny deep capsule network, International Journal of Machine Learning and Cybernetics. 2022, 13(4), 989-1004.
[9] Haixia Xu, Limin Gong, Haizhen Xuan, Xusheng Zheng, Zan Gao, Xianbin Wen. Multiview clustering via consistent and specific nonnegative matrix factorization with graph regularization, Multimedia Systems. 2022, 28(5), 1559-1572.
[10] Guowei Wang, Haixia Xu, Xinyu Wang, Liming Yuan, Xianbin Wen. Remote sensing scene image classification model based on multi-scale features and attention mechanism, Journal of Applied Remote Sensing. 2022 16(4), 044510.
[11] Quan Wang, Haixia Xu, Liming Yuan, Xianbin Wen. Dense capsule network for SAR automatic target recognition with limited data, Remote Sensing Letters. 2022, 13(6), 533-543.
[12] Kun Sun, Haixia Xu, Liming Yuan, Xianbin Wen. Deep capsule network regularization based on generative adversarial, Journal of Electronic Imaging. 2021, 30(4), 040501.
Machine Learning (Undergraduate)
Probability Theory and Mathematical Statistics (Undergraduate)
Time Series Analysis (Undergraduate)
