Homepage of Xingxing Wei
Xingxing Wei (韦星星)
Xueyuan Road No.37, Haidian District,
Beijing, P.R. China
I have joined Beihang (BUAA) University as Associate Professor in September, 2019. If you are interested in my research, please contact me!
From 2017 to 2019, I was a PostDoc in the Department of Computer Science and Technology at Tsinghua University, working with Prof. Jun Zhu. Prior to this, I worked in Ant Financial, as a senior algorithm engineer. In July 2015, I obtained my PhD degree in School of Computer Science and Technology at Tianjin University. In July 2010, I received my bachelor degree in School of Automation and Electrical Engineering at Beihang University. From 2012 to 2015, I spent three happy years at Institute of Information Engineering, Chinese Academy of Sciences, as a visiting student. My research interests include: multimedia, adversarial examples, remote sensing, etc.
Xiaojun Jia, Xingxing Wei, Xiaochun Cao, "Identifying and Resisting Adversarial Videos Using Temporal Consistency", arXiv preprint arXiv:1909.04837, 2019.
Topic: Adversarial Attacks and Defense
Xingxing Wei, Huanqian Yan, Bo Li, "Sparse Black-box Video Attack with Reinforement Learning", International Journal of Computer Vision (IJCV), 2022, accepted.
Xingxing Wei, Ying Guo, Jie Yu, "Adversarial Sticker: A Stealthy Attack Method in the Physical World", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022, accepted
Yikun Xu, Xingxing Wei*, "A2SC: Adversrial Attack on Subspace Clustering", IEEE International Conference on Mutimedia and Expo (ICME), 2022, accepted.
Huanqian Yan, Xingxing Wei* "Efficient Sparse Attacks on Videos using Reinforcement Learning", in ACM International Conference on Multimedia (ACMMM), 2021, accepted.
Siyuan Liang, Baoyuan Wu, Yanbo Fan, Xingxing Wei, , Xiaochun Cao "Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object detection", in the proceeding of International Conference on Computer Vision (ICCV), 2021, accepted.
Siyuan Liang, Xingxing Wei, Xiaochun Cao "Generate More Imperceptible Adversarial Examples for Object Detection" in Workshop on Adversarial Machine Learning at ICML2021.
Xiaojun Jia, Huanqian Yan, Yonglin Wu, Xingxing Wei*, Xiaochun Cao, Yong Zhang "An Effective and Robust Detector for Logo Detection", arXiv:2108.00422, Won the runner-up within 36489 teams in Robust Logo Detection held by ACMMM2021
Guoqiu Wang, Huanqian Yan, Ying Guo, Xingxing Wei* "Improving Adversarial Transferability with Gradient Refining" in Workshop on AML-CV at CVPR2021, Won the 4-th place within 1559 teams about Unrestricted Adversarial Attacks on Imagenet held by CVPR2021.
Yusheng Zhao, Huanqian Yan, Xingxing Wei* "Object Hider: Adversarial Patch Attack Against Object Detectors", arXiv preprint arXiv:2010.14974, Won the 7-th place within 1701 teams in Adversarial Challenge on Object Detection organized by Alibaba in CIKM2020.
Xingxing Wei*, Ying Guo, Bo Li "Black-box Adversarial Attacks by Manipulating Image Attributes", Information Sciences (INS), accepted, 2020
Xiaojun Jia, Xingxing Wei*, Xiaochun Cao, Xiaoguang Han "Adv-watermark: A Novel Perturbations for Adversarial Examples", in ACM International Conference on Multimedia (ACMMM), 2020, accepted.
Siyuan Liang, Xingxing Wei*, Siyuan Yao, Xiaochun Cao "Efficient Adversarial Attacks for Visual Object Tracking", in European Conference on Computer Vision (ECCV), 2020, accepted as poster.
Zhipeng Wei, Jingjing Chen, Xingxing Wei*, Lingxi Jiang, Yu-gang Jiang, Tat-Seng Chua, Fengfeng Zhou "Heuristic Black-box Adversarial Attacks on Video Recognition Model", in AAAI Conference on Artificial Intelligence (AAAI), 2020, accepted as oral. Code
Xiaojun Jia, Xingxing Wei*, Xiaochun Cao, Hassan Foroosh "ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples", In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, accepted. Code
Xingxing Wei, Siyuan Liang, Ning Chen, Xiaochun Cao "Transferable Adversarial Attacks for Image and Video Object Detection", International Joint Conferences on Artificial Intelligence (IJCAI), 2019 , accepted as Oral. Code Project
Xingxing Wei, Jun Zhu, Sha Yuan, Hang Su "Sparse Adversarial Perturbations for Videos", in AAAI Conference on Artificial Intelligence (AAAI), 2019, accepted. Code
Xingxing Wei, Jun Zhu, Sitong Feng, Hang Su "Video-to-Video Translation with Global Temporal Consistency", in ACM International Conference on Multimedia (ACMMM), 2018, accepted.
Topic: Remote Sensing
Bo Li, Xiaoyang Xie, Xingxing Wei*, Wenting Tang "Ship Detection and Classification from Optical Remote Sensing Images: A Survey", Chinese Journal of Aeronautics, accepted, 2020
Nan Wang, Bo Li, Xingxing Wei*, Yonghua Zhang, Huanqian Yan "Ship Detection in Spaceborne Infrared Image Based on Lightweight CNN and Multisource Feature Cascade Decision", IEEE Transactions on Geoscience and Remote Sensing (TGRS), accepted, 2020
Xiaoyang Xie, Bo Li, Xingxing Wei* "Ship Detection in Multispectral Satellite Images Under Complex Environment", Remote Sensing, accepted, 2020
Huanqian Yan, Bo Li, Hong Zhang, Xingxing Wei* "An Anti-jamming and Lightweight Ship Detector Designed for Spaceborne Optical Images", IEEE Journal of Selected Topics in Applied Earth Observation and Remote Sensing (IEEE J-STARS), accepted, 2022.
Xingxing Wei, Zhiqiang Tao, Changqing Zhang, Xiaochun Cao "Structured Saliency Fusion Based on Dempster-Shafer Theory", IEEE Signal Processing Letters (SPL), 2015, accepted. (Won the TOP 10% Paper Award in ICIP2016)
Xiaochun Cao (Supervisor), Xingxing Wei, Yahong Han, Xiaowu Chen "An Object-level High-order Contextual Descriptor based on Semantic, Spatial and Scale Cues", IEEE Transactions on Cybernetics (T-Cyb), 2014, accepted.
Xiaochun Cao (Supervisor), Xingxing Wei*, Yahong Han, Dongdai Lin "Robust Face Clustering via Tensor Decomposition", IEEE Transactions on Cybernetics (T-Cyb), 2014, acceped.
Xiaochun Cao (Supervisor), Xingxing Wei, Xiaojie Guo, Yahong Han, Jinhui Tang "Augmenting Image Retrieval using Multi-order Object Layout with Attributes", in ACM International Conference on Multimedia (ACMMM), 2014, accepted.
Xiaochun Cao (Supervisor), Xingxing Wei, Yahong Han, Yi Yang, DongDai Lin "Robust Tensor Clustering with Non-Greedy Maximization", International Joint Conferences on Artificial Intelligence (IJCAI), 2013.
Xiaochun Cao (Supervisor), Xingxing Wei, Yahong Han, Yi Yang, Nicu Sebe, Alexander Hauptmann "Unified Dictionary Learning and Region Tagging with Hierarchical Sparse Representation", Computer Vision and Image Understanding (CVIU), 117(2013) 934-946.
Xiaochun Cao (Supervisor), Ling Du, Xingxing Wei, Dan Meng, Xiaojie Guo "High Capacity Reversible Data Hiding in Encrypted Images by Patch-level Sparse Representation", IEEE Transactions on Cybernetics (T-Cyb), 2015, accepted.
Yahong Han, Xingxing Wei, Xiaochun Cao, Yi Yang, Xiaofang Zhou "Augmenting Image Descriptions Using Structured Prediction Output", IEEE Transactions on Multimedia (T-MM), 2014, accepted.
Xingxing Wei, Xiaochun Cao, Yahong Han "A Structured Image Description Method", No.201310504488.7
Xingxing Wei, Xiaochun Cao, Yahong Han "A Hierarchical Structure based Image Search Method", No.201310505213.5
Principal Investigator, “The Study of Robust Video Understanding Algorithms based on Encoded Structured Information”, National Natural Science Foundation of China, January 1, 2019 – December 31, 2021.
Principal Investigator, “Robust Video Understanding Algorithms towards Adversarial Examples”, China Postdoctoral Science Special Foundation, January 1, 2019 – December 31, 2019.
Principal Investigator, "The Generation and Defense against Adversarial Examples Towards Video Data", China Postdoctoral Science Foundation, October 1, 2018 – September 30, 2019.
Reviewers of IJCV; TNNLS; AAAI 2019, 2020; ICML 2019; IJCAI2019, 2020; NeurIPS2019, 2020; ACMMM2019, 2020; CVPR2020, etc
Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.