Xin-Shun Xu is a professor at School of Software, Shandong University. He is  the  founder and leader of MIMA (Machine Intelligence and Media Analysis) Group.  He received his M.S. degree in Computer Science from Shandong University, China in 2002, and Ph.D. degree in computer science from University of Toyama, Japan in 2005. In the same year, he joined School of Computer Science and Technology, Shandong University, as an associate professor. From 2009 to 2012, he was a postdoctoral fellow in LAMDA Group, led by professor Zhi-Hua Zhou. His research interests include machine learning, information retrieval, pattern recognition, data mining, etc. Now, he is working on learning to hash, multi-instance Learning, multi-label learning, semi-supervised learning, ensemble learning, deep learning, scene text detection and recognition, media content analysis & retrieval. He has published in TIP, TKDE, TMM, TCSVT, TCYB, AAAI, CIKM, IJCAI, MM, SIGIR, WWW and other venues. He also serves as an area chair or a program committee member or reviewer for various international conferences and journals, e.g., AAAI, CIKM, CVPR, ICCV, IJCAI, MM, TCSVT, TCYB, TIP, TKDE, TMM, TNNLS and TPAMI.

——————————————————————————————————————

Selected Publications：

[1]     Peng-Fei Zhang, Zi Huang, Xin-Shun Xu. Effective and Robust Adversarial Training against Data and Label Corruptions. IEEE Transactions on Multimedia, 2024. (Accepted)

[2]     Zhen-Duo Chen, Li-Jun Zhao, Zi-Chao Zhang, Xin Luo, Xin-Shun Xu. Characteristics Matching Based Hash Codes Generation for Efficient Fine-grained Image Retrieval.  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (Accepted)

[3]     Yu-Wei Zhan, Xin Luo, Zhen-Duo Chen, Yongxin Wang, Yinwei Wei, Xin-Shun Xu. POLISH: Adaptive Online Cross-Modal Hashing for Class Incremental Data. The Web Conference (WWW), 2024. (Accepted)

[4]     Zhen-Xiang Ma, Zhen-Duo Chen, Li-Jun Zhao, Zi-Chao Zhang, Xin Luo, Xin-Shun Xu. Cross-Layer and Cross-Sample Feature Optimization Network for Few-Shot Fine-Grained Image Classification. AAAI Conference on Artificial Intelligence (AAAI), 2024.

[5]     Jia-Nan Li, Xiao-Qian Liu, Xin Luo, Xin-Shun Xu. VOLTER: Visual Collaboration and Dual-Stream Fusion for Scene Text Recognition. IEEE Transactions on Multimedia, 2023. (Accepted)

[6]     Xiao-Qian Liu, Xue-Ying Ding, Xin Luo, Xin-Shun Xu. ProtoUDA: Prototype-based Unsupervised Adaptation for Cross-Domain Text Recognition. IEEE Transactions on Knowledge and Data Engineering, 2023. (Accepted)

[7]     Yongxin Wang, Yu-Wei Zhan, Zhen-Duo Chen, Xin Luo, Xin-Shun Xu. Multiple Information Embedded Hashing for Large-Scale Cross-Modal Retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 2023. (Accepted)

[8]     Hao-Chen Pei, Hao Fang, Xin Luo, and Xin-Shun Xu. Gradformer: A Framework for Multi-Aspect Multi-Granularity Pronunciation Assessment. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2023. (Accepted)

[9]     Zi-Chao Zhang, Zhen-Duo Chen, Yongxin Wang, Xin Luo, Xin-Shun Xu. A vision transformer for fine-grained classification by reducing noise and enhancing discriminative information. Pattern Recognition, 145, 109979, 2024.

[10]  Zi-Chao Zhang, Zhen-Yu Xie, Zhen-Duo Chen, Yu-Wei Zhan, Xin Luo, Xin-Shun Xu. Expansion window local alignment weighted network for fine-grained sketch-based image retrieval. Pattern Recognition, 144, 10989, 2023.

[11]  Chong-Yu Zhang, Xin Luo, Yu-Wei Zhan, Peng-Fei Zhang, Zhen-Duo Chen, Yongxin Wang, Xun Yang, Xin-Shun Xu. Self-Distillation Dual-Memory Online Hashing with Hash Centers for Streaming Data Retrieval. ACM International Conference on Multimedia, 6340-6349, 2023. (Accepted)

[12]  Zi-Chao Zhang, Zhen-Duo Chen, Zhen-Yu Xie, Xin Luo, Xin-Shun Xu. S3Mix: Same Category Same Semantics Mixing for Augmenting Fine-grained Images. ACM Transactions on Multimedia Computing, Communications and Applications, 20(1): 1-16, 2023. (Accepted)

[13]  Xiao-Qian Liu, Xue-Ying Ding, Xin Luo, Xin-Shun Xu. Unsupervised Domain Adaptation via Class Aggregation for Text Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2023. (Accepted)

[14]  Tian-Zi Niu, Shan-Shan Dong, Zhen-Duo Chen, Xin Luo, Shanqing Guo, Xin-Shun Xu. Semantic Enhanced Video Captioning with Multi-feature Fusion. ACM Transactions on Multimedia Computing Communications and Applications, 2023. (Accepted)

[15]  Tian-Zi Niu, Zhen-Duo Chen, Xin Luo, Peng-Fei Zhang, Zi Huang, and Xin-Shun Xu. Video Captioning by Learning from Global Sentence and Looking Ahead. ACM Transactions on Multimedia Computing Communications and Applications, 2023. (Accepted)

[16]  Xue-Ying Ding, Xiao-Qian Liu, Xin Luo, Xin-Shun Xu. DOC: Text Recognition via Dual Adaptation and Clustering. IEEE Transactions on Multimedia, 2023. (Accepted)

[17]  Tian-Zi Niu, Shan-Shan Dong, Zhen-Duo Chen, Xin luo, Zi Huang, Shanqing Guo, Xin-Shun Xu. A Multi-layer Memory Sharing Network for Video Captioning. Pattern Recognition, 2022. (Accepted)

[18]  Jie-Ru Tian, Yongxin Wang, Zhen-Duo Chen, Xin Luo, Xin-Shun Xu. Diagnose Like Doctors: Weakly-Supervised Fine-Grained Classification of Breast Cancer. ACM Transactions on Intelligent Systems and Technology, 2022. (Accepted)

[19]  Yongxin Wang, Zhen-Duo Chen, Xin Luo, Xin-Shun Xu. A High-Dimensional Sparse Hashing Framework for Cross-Modal Retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 2022.

[20]  Shan-Shan Dong, Tian-Zi Niu, Xin Luo, Wu Liu, Xin-Shun Xu. Semantic Embedding Guided Attention with Explicit Visual-feature Fusion for Video Captioning. ACM Transactions on Multimedia Computing Communications and Applications, 2022. (Accepted)

[21]  Peng-Fei Zhang, Zi Huang, Guangdong Bai, Xin-Shun Xu. IDEAL: High-Order-Ensemble Adaptation Network for Learning with Noisy Labels. ACM International Conference on Multimedia (MM), 2022.

[22]  Peng-Fei Zhang, Guangdong Bai, Zi Huang, Xin-Shun Xu. Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach. ACM International Conference on Multimedia (MM), 2022.

[23]  Xinyu Liu, Xiaoqian Liu, Bin Wang, Xin Luo and Xin-Shun Xu. Arbitrary-shaped scene text detection with scoring mask quality.  IEEE International Conference on Multimedia & Expo (ICME), 2022.

[24]  Zhen-Duo Chen, Xin Luo, Yongxin Wang, Shanqing Guo and Xin-Shun Xu. Fine-grained hashing with double filtering. IEEE Transactions on Image Processing, 2022.

[25]  Peng-Fei Zhang, Yang Li, Zi Huang and Xin-Shun Xu. Aggregation-based graph convolutional hashing for unsupervised cross-modal retrieval. IEEE Transactions on Multimedia, 2022.

[26]  Yu-Wei Zhan, Yongxin Wang, Yu Sun, Xiao-Ming Wu, Xin Luo and Xin-Shun Xu.  Discrete online cross-modal hashing. Pattern Recognition, 2022.

[27]  Xiao-Ming Wu, Xin Luo, Yu-Wei Zhan, Chen-Lu Ding, Zhen-Duo Chen and Xin-Shun Xu. Online enhanced semantic hashing: Towards effective and efficient retrieval for streaming multi-modal data. AAAI Conference on Artificial Intelligence (AAAI), 2022.

[28]  Yongxin Wang, Jie-Ru Tian, Zhen-Duo Chen, Xin Luo, Xin-Shun Xu. Label enhancement discrete cross-modal hashing method. Journal of Software, 2022. (Accepted, in Chinese)

[29]  Yan Wang, Yu-Wei Zhan, Xin Luo, Meng Liu,  and Xin-Shun Xu. Survey on video moment retrieval. Journal of Software, 2022. (Accepted, in Chinese)

[30]  Chen-Lu Ding, Xin Luo, Xiao-Ming Wu, Yu-Wei Zhan, Rui Li, Hui Zhang, and Xin-Shun Xu. Weakly-Supervised Online Hashing with Refined Pseudo Tags. ACM International Conference on Information and Knowledge Management (CIKM), 2022.  (Accepted)

[31]  Yongxin Wang, Zhen-Duo Chen, Xin Luo, Rui Li and Xin-Shun Xu. Fast cross-modal hashing with global and local similarity embedding. IEEE Transactions on Cybernetics, 2021.

[32]  Yu-Wei Zhan, Xin Luo, Yu Sun, Yongxin Wang, Zhen-Duo Chen and Xin-Shun Xu.  Weakly-supervised online hashing. IEEE International Conference on Multimedia & Expo (ICME), 2021.

[33]  Hong-Lei Yao, Yu-Wei Zhan, Zhen-Duo Chen, Xin Luo and Xin-Shun Xu. TEACH:  Attention-aware deep cross-modal hashing. ACM International Conference on Multimedia Retrieval (ICMR), 2021.

[34]  Hui-Qiong Li, Yongxin Wang, Zhen-Duo Chen, Xin Luo and Xin-Shun Xu. Ranking-based supervised discrete cross-modal hashing. Chinese Journal of Computers, 2021. (In Chinese)

[35]  Peng-Fei Zhang, Yadan Luo, Zi Huang, Xin-Shun Xu and Jingkuan Song. High-order nonlocal hashing for unsupervised cross-modal retrieval. World Wide Web, 2021.

[36]  Peng-Fei Zhang, Zi Huang and Xin-Shun Xu. Proactive privacy-preserving learning for retrieval. AAAI Conference on Artificial Intelligence (AAAI), 2021.

[37]  Yongxin Wang, Zhen-Duo Chen, Xin Luo and Xin-Shun Xu. High-dimensional sparse cross-modal hashing with fine-grained similarity embedding.  International World Wide Web Conference (WWW), 2021.

[38]  Yongxin Wang, Xin Luo, Liqiang Nie, Jingkuan Song, Wei Zhang and Xin-Shun Xu.  BATCH: A scalable asymmetric discrete cross-modal hashing. IEEE Transactions on Knowledge and Data Engineering, 2020. 

[39]  Xianjing Han, Xuemeng Song, Yiyang Yao, Xin-Shun Xu and Liqiang Nie. Neural compatibility modeling with probabilistic knowledge distillation.  IEEE Transactions on Image Processing, 2020.

[40]  Yongxin Wang, Xin Luo and Xin-Shun Xu. Label embedding online hashing for cross-modal retrieval. ACM International Conference on Multimedia (MM), 2020.

[41]  Yu-Wei Zhan, Xin Luo, Yongxin Wang and Xin-Shun Xu. Supervised hierarchical deep hashing for cross-modal retrieval. ACM International Conference on Multimedia (MM), 2020.

[42]  Zhen-Duo Chen, Chuan-Xiang Li, Xin Luo, Liqiang Nie, Wei Zhang and Xin-Shun Xu.  SCRATCH: A scalable discrete matrix factorization hashing framework for cross-modal retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 2020.

[43]  Zhen-Duo Chen, Yongxin Wang, Hui-Qiong Li, Xin Luo, Liqiang Nie and Xin-Shun Xu.  A two-step cross-modal hashing by exploiting label correlations and preserving similarity in both steps. ACM International Conference on Multimedia (MM), 2019.

[44]  Xuemeng Song, Xianjing Han, Yunkai Li, Jingyuan Chen, Xin-Shun Xu and Liqiang Nie. GP-BPR: Personalized compatibility modeling for clothing matching.  ACM International Conference on Multimedia (MM), 2019.

[45]  Yongqi Li, Meng Liu, Jianhua Yin, Chaoran Cui, Xin-Shun Xu and Liqiang Nie.  Routing micro-videos via a temporal graph-guided recommendation system.  ACM International Conference on Multimedia (MM), 2019.

[46]  Xue Dong, Xuemeng Song, Fuli Feng, Peiguang Jing, Xin-Shun Xu and Liqiang Nie. Personalized capsule wardrobe creation with garment and user  modeling. ACM International Conference on Multimedia (MM), 2019.

[47]  Jingkuan Song, Xiaosu Zhu, Lianli Gao, Xin-Shun Xu, Wu Liu and Heng Tao Shen.  Deep recurrent quantization for generating sequential binary codes.  International Joint Conference on Artificial Intelligence (IJCAI), 2019.

[48]  Chen Cui, Wenjie Wang, Xuemeng Song, Minlie Huang, Xin-Shun Xu and Liqiang Nie. User attention-guided multimodal dialog systems. International ACM SIGIR Conference of Research and Development in Information Retrieval (SIGIR), 2019.

[49]  Chuan-Xiang Li, Ting-Kun Yan, Xin Luo, Liqiang Nie and Xin-Shun Xu. Supervised robust discrete multimodal hashing for cross-media retrieval. IEEE Transactions on Multimedia, 2019.

[50]  Heyan Huang, Xiaochi Wei, Liqiang Nie, Xianling Mao and Xin-Shun Xu. From question to text: Question-oriented feature attention for answer selection. ACM Transactions on Information and System Security, 2019.

[51]  Xin Luo, Ye Wu, Wan-Jin Yu and Xin-Shun Xu. Class consistent hashing for fast web data searching. World Wide Web, 2019.

[52]  Yongxin Wang, Xin Luo, Huaxiang Zhang and Xin-Shun Xu. Sparse manifold embedded hashing for multimedia retrieval. ICDE Workshops, 2019.

[53]  Wan-Jin Yu, Zhen-Duo Chen, Xin Luo, Wu Liu and Xin-Shun Xu. DELTA: A deep dual-stream network for multi-label image classification. Pattern Recognition, 2019.

[54]  Xin Luo, Peng-Fei Zhang, Zi Huang, Liqiang Nie and Xin-Shun Xu. Discrete hashing with multiple supervision. IEEE Transactions on Image Processing, 2019.

[55]  Wei Zhang, Yimeng Li, Weizhi Lu, Xin-Shun Xu and Xiangyang Ji. Learning intra-video difference for person re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 2019.

[56]  Chuan-Xiang Li, Zhen-Duo Chen, Peng-Fei Zhang, Xin Luo, Liqiang Nie, Wei Zhang and Xin-Shun Xu. SCRATCH: A scalable discrete matrix factorization hashing for cross-modal retrieval. ACM International Conference on Multimedia (MM), 2018.

[57]  Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Xin-Shun Xu and Mohan Kankanhalli.  Multi-modal preference modeling for product search. ACM International Conference on Multimedia (MM), 2018.

[58]  Xin Luo, Xiao-Ya Yin, Liqiang Nie, Xuemeng Song, Yongxin Wang and Xin-Shun Xu. SDMCH: Supervised discrete manifold-embedded cross-modal hashing.  International Joint Conference on Artificial Intelligence (IJCAI), 2018.

[59]  Xin Luo, Liqiang Nie, Xiangnan He, Ye Wu, Zhen-Duo Chen and Xin-Shun Xu.  Fast scalable supervised hashing. International ACM SIGIR Conference of Research and Development in Information Retrieval (SIGIR), 2018.

[60]  Wenjie Wang, Minlie Huang, Xin-Shun Xu, Fumin Shen and Liqiang Nie. Chat more:  Deepening and widening the chatting topic via a deep model.  International ACM SIGIR Conference of Research and Development in Information Retrieval (SIGIR), 2018.

[61]  Ye Wu, Xin Luo, Xin-Shun Xu, Shanqing Guo and Yuliang Shi. Dictionary learning based supervised discrete hashing for cross-media retrieval.  ACM International Conference on Multimedia Retrieval (ICMR), 2018.

[62]  Xin Luo, Peng-Fei Zhang, Ye Wu, Zhen-Duo Chen, Hua-Junjie Huang and Xin-Shun Xu. Asymmetric discrete cross-modal hashing. ACM International Conference on Multimedia Retrieval (ICMR), 2018.

[63]  Xin Luo, Ye Wu and Xin-Shun Xu. Scalable supervised discrete hashing for large-scale search. International World Wide Web Conference (WWW), 2018. 

[64] Zhen-Duo Chen, Wan-Jin Yu, Chuan-Xiang Li, Liqiang Nie and Xin-Shun Xu. Dual deep neural networks cross-modal hashing. AAAI Conference on Artificial Intelligence (AAAI), 2018.