Note: this page will not be updated. Please visit this new homepage: https://wangxiao5791509.github.io/ 

About Me

I received the B.S. degree and the Ph.D. degree from West Anhui University (Luan, China, in 2013) and Anhui University (Hefei, China, in 2019). In my Ph.D. career, I was supervised by Professor Jin Tang and Bin Luo (Lab: Multi-Modal Intelligent Computing Group). From 2015 and 2016, I was a visiting student at the School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China, and supervised by Professor Liang Lin. From 7 July to 20 November 2019, I was studying in the J17 Sydney Data Science Hub, University of Sydney, and supervised by Professor Dacheng Tao. From 9 April 2020 to 8 April 2022, I begin my Postdoc career at Pengcheng Laboratory (Shenzhen, China) and cooperate with Professor Feng Wu, Yonghong Tian, and Yaowei Wang. Currently, I work at the School of Computer Science and Technology of  Anhui University, Hefei, China, as an Associate Professor. My current research interests are mainly in vision-based artificial intelligence and pattern recognition, especially in Motion Detection and Tracking. I am a reviewer for IEEE TCSVT, TIP, IJCV, PR, CVPR, ICCV, AAAI, ECCV, ACCV, ACM-MM, and WACV.

Research Topic 

• Object Tracking: Single-, Multi-Object Tracking 

• Multi-modal: Vision-Language, Vision-Thermal (Infrared), Vision-Depth, Vision-Event, Vision-Audio  

• Neuromorphic Vision: Detection and Tracking, Action Recognition, Scene Reconstruction 

News

• 2022.05.13        Working as an Associate Professor at the School of Computer Science and Technology, Anhui University, Hefei, China.   

• 2022.05.08      "MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking" was accepted by IEEE TMM 2022 [Paper] [Code]

• 2022.03.29      "Event-based Video Reconstruction via Potential-assisted Spiking Neural Network" was accepted by CVPR-2022, Poster. 

• 2022.03.25      Complete defense of my postdoc research "Research on Non-greedy Search and Multi-Modal Information Fusion Guided Visual Tracking". 

• 2021.12.01     "Retinomorphic Object Detection in Asynchronous Visual Streams" was accepted by AAAI 2022, Oral. 

• 2021.10.30     "Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark" was accepted by IEEE T-CSVT 2021 [IEEE version]

• 2021.10.08     Our dataset paper TNL2K is selected as the workshop spotlight in VALSE 2021, Hangzhou [Photo].

• 2021.08.20     I was supported by the National Natural Science Foundation of China (青年科学基金项目 2022-2024). 

• 2021.08.12       The first large-scale neuromorphic tracking dataset VisEvent is released at [arxiv]. 

• 2021.08.09     "RGBT Tracking via Cross-modality Message Passing" was accepted by Neurocomputing 2021. 

• 2021.07.31     "Pedestrian Attribute Recognition: A Survey", was accepted by Pattern Recognition 2021. 

• 2021.07.23     Two papers (as the co-author) were accepted by ICCV-2021. 

• 2021.06.01      "Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark" is available on [arxiv] 

• 2021.05.21      "Tracking by Joint Local and Global Search: A Target-aware Attention based Approach" was accepted by IEEE TNNLS 2021 [arxiv]

• 2021.03.01      "Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark" was accepted by CVPR-2021

• 2021.01.19       "Dynamic Attention-guided Multi-Trajectory Analysis for Single Object Tracking" was accepted by IEEE TCSVT 2021 [Paper]. 

• 2020.11.03      I was supported by the China Postdoctoral Science Foundation Funded Project (中国博士后科学基金第68批面上资助 ) [News]

• 2020.08.26    The camera for fast object sensing in our lab was reported by CCTV-CGTN "Shenzhen uses AI for epidemic prevention" [News]  

• 2020.07.08    Pre-print of "STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification" is available on [arxiv] [Code]. 

• 2020.06.24    I was selected as the “Postdoctoral Innovative Talent Support Program” of 2020 (第5批博士后创新人才支持计划)  [Chinapostdoctor] [News]

• 2020.06.04    Source code of "cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks" was released at [Github]. 

• 2020.05.25    Source code of "Dynamic Modality-Aware Filter Generation for RGB-T Tracking" is available at [Github]. 

• 2020.05.07    "cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks" was accepted by IEEE TMM 2021.   

• 2020.04.09    Join Pengcheng Laboratory. 

Selected Publications

• MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking, Xiao Wang, Xiujun Shu, Shiliang Zhang, Bo Jiang, Yaowei Wang, Yonghong Tian, Feng Wu, IEEE TMM 2022, [arXiv] [IEEE] [Code]

• Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition, Peipei Zhu, Xiao Wang, Yong Luo, Zhenglong Sun, Wei-Shi Zheng, Yaowei Wang, Changwen Chen, 2022, in peer review [arxiv]

• Tiny Object Tracking: A Large-scale Dataset and A Baseline, Yabin Zhu, Chenglong Li, Yao Liu, Xiao Wang, Jin Tang, Bin Luo, Zhixiang Huang, 2022, in peer review [arxiv] [github]

• Event-based Video Reconstruction via Potential-assisted Spiking Neural Network, Lin Zhu, Xiao Wang, Yi Chang, Jianing Li, Tiejun Huang, Yonghong Tian,  CVPR 2022 [Paper] [Code]

• MutualFormer: Multi-Modality Representation Learning via Mutual Transformer [J]. Wang, Xixi and Jiang, Bo and Wang, Xiao and Luo, Bin,  arXiv preprint arXiv:2112.01177, 2021. [Paper] 

• Retinomorphic Object Detection in Asynchronous Visual Streams, Jianing Li, Xiao Wang, Lin Zhu, Jia Li, Tiejun Huang, Yonghong Tian, AAAI-2022, Oral, [Paper] [Poster] 

• VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows, Xiao Wang, Jianing Li, Lin Zhu, Zhipeng Zhang, Zhe Chen, Xin Li, Yaowei Wang, Yonghong Tian, Feng Wu [Paper] [Project] [Demo] [VideoTutorial] [Dataset, Source Code, and Evaluation Toolkit]

• Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search, In Peer Review, Xiao Wang, Zhe Chen, Bo Jiang, Jin Tang, Bin Luo, Dacheng Tao [Paper] [Code] [Project] [Video] 

• RGBT Tracking via Cross-modality Message Passing, Neurocomputing 2021, Rui Yang, Xiao Wang, Chenglong Li, Jinmin Hu, Jin Tang [Paper]

• Learn to Match: Automatic Matching Network Design for Visual Tracking, Zhipeng Zhang, Yihao Liu, Xiao Wang, Bing Li, Weiming Hu, ICCV-2021 [Paper] [Code] [DemoVideo] [Poster] 

• NeuSpike-Net: High Speed Image Reconstruction via Bio-inspired Neuromorphic Cameras, Lin Zhu, Jianing Li, Xiao Wang, Tiejun Huang, Yonghong Tian, ICCV-2021 [Paper] [Project]

• Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification, Xiujun Shu; Ge Li; Xiao Wang; Weijian Ruan; Qi Tian, IEEE Signal Processing Letters (2021), [Paper] [Arxiv] [Code]  

• Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark, Xiujun Shu, Xiao Wang, Shiliang Zhang, Xianghao Zhang, Yuanqi Chen, Ge Li, Qi Tian, IEEE T-CSVT 2021 [Paper] [Project] [Code] [Dataset [BaiduYun (code: vvfe)] [Onedrive] [Googledrive]]

• Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark， Xiao Wang, Xiujun Shu, Zhipeng Zhang, Bo Jiang, Yaowei Wang, Yonghong Tian, Feng Wu, CVPR-2021, [Paper] [Dataset] [Project] [EvaluationToolKit][Demo] [Tutorial]

• Tracking by Joint Local and Global Search: A Target-aware Attention based Approach, Xiao Wang, Jin Tang, Bin Luo, Yaowei Wang, Yonghong Tian, and Feng Wu, IEEE TNNLS 2021. [arxiv] [IEEE] [Code] [Video]

• STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification, Bo Jiang · Sheng Wang · Xiao Wang* · Aihua Zheng, arxiv preprint arXiv:2007.03584, [Paper] [Code] 

• cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks, Bo Jiang, Zitai Zhou, Xiao Wang*, Jin Tang, Bin Luo, IEEE T-MM.  (* denotes the corresponding author) [Paper] [Project] [Code]

• Dynamic Attention-guided Multi-Trajectory Analysis for Single Object Tracking, Xiao Wang, Zhe Chen, Jin Tang, Bin Luo, Yaowei Wang, Yonghong Tian, Feng Wu, IEEE TCSVT 2021 [arxiv] [Paper] [Project] [Code]

• Describe and Attend to Track: Learning Natural Language guided Structural Representation and Visual Attention for Object Tracking, Xiao Wang, Chenglong Li, Rui Yang, Tianzhu Zhang, Jin Tang, Bin Luo, arXiv Pre-print [Project] [Paper]

• Quality–aware dual–modal saliency detection via deep reinforcement learning, Xiao Wang, Tao Sun, Rui Yang, Chenglong Li, Bin Luo, and Jin Tang.  Signal Processing and Image Communication (2019).  [Paper] 

• Learning Target-aware Attention for Robust Tracking with Conditional Adversarial Network, Xiao Wang, Tao Sun, Rui Yang, Bin Luo, BMVC-2019, [Project] [Paper] [Supplementary Material]

• Pedestrian Attribute Recognition: A Survey, Pattern Recognition-2021, Xiao Wang, Shaofei Zheng, Rui Yang, Aihua Zheng, Zhe Chen, Bin Luo, Jin Tang, [Project] [Paper] [Github] [PR-Version]

• Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity, Xiao Wang, Ziliang Chen, Rui Yang, Jin Tang, Bin Luo, arXiv [Project-page] [Paper] 

• Learning Target-oriented Dual Attention for Robust RGB-T Tracking, Rui Yang, Yabin Zhu, Xiao Wang, Chenglong Li, Jin Tang, ICIP-2019. [Paper]

• Dense Feature Aggregation and Pruning for RGBT Tracking, Yabin Zhu, Chenglong Li, Bin Luo, Jin Tang, Xiao Wang, ACM MM 2019 [Paper]

• Multi-modal foreground detection via inter-and intra-modality-consistent low-rank separation. Neurocomputing. Zheng, Aihua and Ye, Naipeng and Li, Chenglong and Wang, Xiao and Tang, Jin  [Paper]

• Sint++: robust visual tracking via adversarial positive instance generation, Xiao Wang, Chenglong Li, Bin Luo, and Jin Tang. IEEE CVPR-2018. [Project] [Paper] 

• Weighted low-rank decomposition for robust grayscale-thermal foreground detection, Li, Chenglong+, Xiao Wang+, Lei Zhang, Jin Tang, Hejun Wu, and Liang Lin. (+ equal contribution) IEEE TCSVT 2017   [Project-page]  [Paper]

• Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning[J].Chen Ziliang, Wang Keze, Xiao Wang, et al.  IEEE TCSVT 2017. [Paper]

• Grayscale-Thermal Object Tracking via Multitask Laplacian Sparse Representation [J]. Li Chenglong, Sun Xiang, Xiao Wang, et al.  IEEE T-SMCS 2017 [Paper]