Dr. Xiaoshuai Sun (孙晓帅)

Associate Professor, MAC Lab

School of Informatics, Xiamen University

Office: Room B705, Haiyu Administration Building, XMU Haiyun Campus

Email: xssun(at)xmu.edu.cn, xiaoshuaisun.hit[at]gmail.com Google Scholar

Dr. Xiaoshuai Sun is an associate professor of School of Informatics, Xiamen University, China. He has been working as an assistant professor at School of Computer Science and Technology, Harbin Institute of Technology, from Sep. 2016 to May. 2019. From Sep. 2015 to Dec. 2016, he was a post-doc research fellow with Prof. Heng Tao Shen and Prof. Zi Huang at School of Information Technology and Electrical Engineering, the University of Queensland, Australia. He received his doctoral degree from Harbin Institute of Technology in January 2015 under the supervision of Prof. Hongxun Yao. From September 2012 to June 2013, he worked as a research intern in Microsoft Research Asia (MSRA) mentored by Dr. Xin-Jing Wang. His current research interests include deep learning, computer vision and pattern recognition, multimedia content analysis and retrieval. He has published over 60 papers as the main author, and most of them have been published in reputed journals and top international conferences including IEEE TIP, PR, IEEE CVPR, AAAI, ACM Multimedia.

Recent News

  • [25 Jul 2020] 4 papers have been accepted by ACM MM 2020.

  • [14 Nov 2019] Our paper " Plenty Is Plague: Fine-Grained Learning for Visual Question Answering" has been accepted by TPAMI.

  • [11 Nov 2019] Our paper " SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation" has been accepted by AAAI 2020.

  • [3 Sep 2019] 2 papers have been accepted by NIPS 2019.

  • [1 Nov 2018] 4 papers have been accepted by AAAI 2019.

Awards

  • Excellent Ph.D Thesis Award of Harbin Institute of Technology, 2015

  • Best Student Paper Award, Harbin Institute of Technology, 2013

  • National Scholarship for Ph.D Student, Harbin Institute of Technology, 2012

  • Microsoft Fellowship, Microsoft Research Asia, 2011

  • Guanghua & Guorui Scholarship, Harbin Institute of Technology, 2009-2010

  • Excellent Graduate of Harbin Engineering University, 2007

  • Excellent Graduate of Heilongjiang Province, China, 2007

Publications (Google Scholar, GitHub)

2021

Conference:

  • Xuying Zhang, Xiaoshuai Sun*, Yunpeng Luo, Jiayi Ji, Yiyi Zhou, Yongjian Wu, Feiyue Huang, Rongrong Ji. RSTNet: Captioning with Adaptive Attention on Visual and Non-Visual Words, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

  • Jiayi Ji, Yunpeng Luo, Xiaoshuai Sun*, Fuhai Chen, Gen Luo, Yongjian Wu, Yue Gao, Rongrong Ji, Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network, The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021

  • Yunpeng Luo, Jiayi Ji, Xiaoshuai Sun*, Liujuan Cao, Yongjian Wu, Feiyue Huang, Chia-Wen Lin, Rongrong Ji, Dual-level Collaborative Transformer for image captioning, The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021

2020

Journal:

  • Mingbao Lin, Rongrong Ji, Hong Liu, Xiaoshuai Sun, Shen Chen, Qi Tian. Hadamard Matrix Guided Online Hashing. IJCV, 2020, In Press.

  • Tingting Han, Hongxun Yao, Wenlong Xie, Xiaoshuai Sun, Sicheng Zhao, Jun Yu. TVENet: Temporal variance embedding network for fine-grained action representation. Pattern Recognition (PR), 103: 107267 (2020).

  • Sheng Jin, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Lei Zhang, Xian-Sheng Hua. Deep Saliency Hashing for Fine-Grained Retrieval. IEEE Transactions on Image Processing (TIP) 29: 5336-5351 (2020).

Conference:

  • Xiaoshuai Sun, Xuying Zhang, Liujuan Cao*, Yongjian Wu, Feiyue Huang, Rongrong Ji, Exploring Language Prior for Mode-Sensitive Visual Attention Modeling, ACM Multimedia 2020, accepted

  • Yiyi Zhou, Rongrong Ji, Xiaoshuai Sun*, Gen Luo, Xiaopeng Hong, Jingsong Su, Xinghao Ding, Ling Shao, K-armed Bandit based Multi-Modal Network Architecture Search for Visual Question Answering, ACM Multimedia 2020, accepted

  • Jiayi Ji, Xiaoshuai Sun*, Yiyi Zhou, Rongrong Ji, Fuhai Chen, Jianzhuang Liu, Qi Tian, Attacking Image Captioning Towards Accuracy-Preserving Target Words Removal, ACM Multimedia 2020, accepted

  • Gen Luo, Yiyi Zhou*, Rongrong Ji, Xiaoshuai Sun, Jingsong Su, Chia-Wen Lin, Qi Tian, Cascade Grouped Attention Network for Referring Expression Segmentation, ACM Multimedia 2020, accepted

  • Gen Luo, Yiyi Zhou, Xiaoshuai Sun, Liujuan Cao, Chenlin Wu, Cheng Deng, Rongrong Ji, Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation, CVPR 2020, Oral.

  • Sheng Jin, Shangchen Zhou, Yao Liu, Chao Chen, Xiaoshuai Sun, Hongxun Yao, Xiansheng Hua. SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation, AAAI 2020.

2019

Journal:

  • Yiyi Zhou, Rongrong Ji, Xiaoshuai Sun, Jinsong Su, Deyu Meng, Yue Gao, Chunhua Shen. Plenty Is Plague: Fine-Grained Learning for Visual Question Answering. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted.

  • Rongrong Ji, Ke Li, Yan Wang, Xiaoshuai Sun, Feng Guo, Xiaowei Guo, Yongjian Wu, Feiyue Huang, Jiebo Luo. Semi-Supervised Adversarial Monocular Depth Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted.

  • Taisong Jin, Rongrong Ji, Yue Gao, Xiaoshuai Sun, Xibin Zhao, Dacheng Tao. Correntropy-Induced Robust Low-Rank Hypergraph. IEEE Transactions on Image Processing (TIP) 28(6): 2755-2769

  • Wenlong Xie, Hongxun Yao, Xiaoshuai Sun, Tingting Han, Sicheng Zhao, Tat-Seng Chua. Discovering Latent Discriminative Patterns for Multi-Mode Event Representation. IEEE Transactions on Multimedia (TMM) 21(6): 1425-1436

  • Jun Peng, Yiyi Zhou, Xiaoshuai Sun, Jinsong Su, Rongrong Ji. Social Media Based Topic Modeling for Smart Campus: A Deep Topical Correlation Analysis Method. IEEE Access 7: 7555-7564

  • Sheng Jin, Hongxun Yao, Xiaoshuai Sun*, Shangchen Zhou. Unsupervised semantic deep hashing. Neurocomputing 351: 19-25

  • Taisong Jin, Zhengtao Yu, Yue Gao, Shengxiang Gao, Xiaoshuai Sun, Cuihua Li. Robust ℓ2-Hypergraph and its applications. Information Science 501: 708-723

  • Xiusheng Lu, Hongxun Yao, Sicheng Zhao, Xiaoshuai Sun, Shengping Zhang. Action recognition with multi-scale trajectory-pooled 3D convolutional descriptors. Multimedia Tools and Applications (MTA) 78(1): 507-523

  • Yasi Wang, Hongxun Yao, Wei Yu, Dong Wang, Shangchen Zhou, Xiaoshuai Sun. Gradual recovery based occluded digit images recognition. Multimedia Tools and Applications (MTA) 78(2): 2571-2586

Conference:

  • Fuhai Chen, Rongrong Ji, Jiayi Ji, Xiaoshuai Sun, Baochang Zhang, Xurui Ge, Yongjian Wu, Feiyue Huang, Yan Wang. Variational Structured Semantic Inference for Diverse Image Captioning, NIPS 2019.

  • Jie Hu, Rongrong Ji, Shengchuan Zhang, Xiaoshuai Sun, Qixiang Ye, Chia-Wen Lin, Qi Tian. Information Competing Process for Learning Diversified Representations, NIPS 2019.

  • Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Shengping Zhang. Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images, ICCV 2019.

  • Huafeng Kuang, Rongrong Ji, Hong Liu, Shengchuan Zhang, Xiaoshuai Sun, Feiyue Huang, Baochang Zhang. Multi-modal Multi-layer Fusion Network with Average Binary Center Loss for Face Anti-spoofing, ACM MM 2019.

  • Taisong Jin, Liujuan Cao, Baochang Zhang, Xiaoshuai Sun, Cheng Deng, Rongrong Ji. Hypergraph Induced Convolutional Manifold Networks, IJCAI 2019.

  • Yiyi Zhou, Rongrong Ji, Jinsong Su, Xiangming Li, Xiaoshuai Sun*. Free VQA Models from Knowledge Inertia by Pairwise Inconformity Learning, AAAI 2019.

  • Yiyi Zhou, Rongrong Ji, Jinsong Su, Xiaoshuai Sun, Weiqiu Chen. Dynamic Capsule Attention for Visual Question Answering, AAAI 2019.

  • Mingbao Lin, Rongrong Ji, Hong Liu, Xiaoshuai Sun. Towards Optimal Discrete Online Hashing with Balanced Similarity, AAAI 2019.

  • Xiawu Zheng, Rongrong Ji, Xiaoshuai Sun, et al. Towards Optimal Fine Grained Retrieval via Decorrelated Centralized Loss with Normalize-Scale layer, AAAI 2019.

2018

Journal:

  • Xuanhan Wang, Lianli Gao, Peng Wang, Xiaoshuai Sun, Xianglong Liu. "Two-stream 3d convnet fusion for action recognition in videos with arbitrary size and length". IEEE Transactions on Multimedia (TMM), 20(3): 634-644, 2018.

  • Wei Yu, Xiaoshuai Sun, Kuiyuan Yang, Yong Rui, Hongxun Yao. "Hierarchical semantic image matching using CNN feature pyramid". Computer Vision and Image Understanding (CVIU), vol. 169, pp. 40-51, 2018.

  • Cheng Pang, Hongxun Yao, Xiaoshuai Sun, Sicheng Zhao, Wei Yu, Rediscover flowers structurally. Multimedia Tools Appl. 77(7): 7851-7863, 2018

  • Cheng Pang, Hongxun Yao, Xiaoshuai Sun, Sicheng Zhao, Yanhao Zhang, Exploring part-aware segmentation for fine-grained visual categorization. Multimedia Tools Appl. 77(23): 30291-30310, 2018.

  • Ying Zheng, Hongxun Yao, Xiaoshuai Sun, Sicheng Zhao, Fatih Porikli. "Distinctive action sketch for human action recognition". Signal Processing, vol.144, pp.323-332, 2018

  • Wenlong Xie, Hongxun Yao, Sicheng Zhao, Xiaoshuai Sun, Tingting Han. "Event patches: Mining effective parts for event detection and understanding". Signal Processing, vol.149, pp.82-87, 2018

Conference:

  • Fuhai Chen, Rongrong Ji, Xiaoshuai Sun, Yongjian Wu, Jinsong Su. "GroupCap: Group-based Image Captioning with Structured Relevance and Diversity Constraints". IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [CCF A]

  • Xiawu Zheng, Rongrong Ji, Xiaoshuai Sun, Yongjian Wu, Feiyue Huang, Yanhua Yang. "Centralized Ranking Loss with Weakly Supervised Localization for Fine-Grained Object Retrieval". The 27th International Joint Conference on Artificial Intelligence (IJCAI), 2018. [CCF A]

  • Tingting Han, Hongxun Yao, Xiaoshuai Sun, Wenlong Xie, Yanhao Zhang. "ADD: Actionness-Pooled Deep-Convolutional Descriptor". IEEE International Conference on Multimedia and Expo (ICME), 2018.

  • Chuang Lin, Hongxun Yao, Wei Yu, Xiaoshuai Sun, Cycle-Consistency Based Hierarchical Dense Semantic Correspondence. ICIP, 2018.

Courses and Tutorials

  • Information Retrieval (INFS7410), the University of Queensland, Australia, Invited Lecturer & Teaching Assistant, 2016.6 - 2016.9

  • Computational Modeling of Visual Attention, the University of Queensland, Australia, Invited Tutorial Speaker of DKE-Lab@UQ, 2016.4.26-27

  • Digital Image Processing, Harbin Institute of Technology, China, Teaching Assistant, 2017.3 - now

  • Multimedia Technology, Harbin Institute of Technology, China, Teaching Assistant, 2017.3 - now

  • Multimedia Data Analysis and Mining, APESS 2018 @ HIT, Invited Lecturer, 2018. 7.31

Authorized Patents

  • Hongxun Yao, Xiaoshuai Sun, Xue Li, "Clothes Style Mining and Recommendation Based on Clothes Image Set", CN 201210104011.5

  • Hongxun Yao, RongrongJi, Xiaoshuai Sun, et al., “Video Scene Correlation Acquisition with Application to Efficient Video Navigation and Retrieval”, CN 200810137510.8

  • Hongxun Yao, Tianqiang liu, RongrongJi, Xiaoshuai Sun, “An action Categorization Method with Spatial Constraint”, CN 200810137503.8