About Me
I am an Associate Researcher at National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences (CASIA). I received my Doctor’s degree at the CASIA. Before that, I received my Master’s degree of Computer Science from Beijing Institute of Technology (BIT).
Research Interest
- Multimedia & Computer Vision:
- Image/Video Analysis, Event Analysis, Attribute Learning
- Pattern Recognition & Machine Learning:
- Sparse Coding, Deep Learning, Transfer Learning
Publications
- Yaguang Song, Junyu Gao, Xiaoshan Yang, Changsheng Xu: Learning Hierarchical Video Graph Networks for One-Stop Video Delivery, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2021
- Yi Huang, Xiaoshan Yang, Junyu Gao, Changsheng Xu: Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition, IEEE Transactions on Multimedia (TMM), 2021
- Chaofan Chen, Xiaoshan Yang, Changsheng Xu, Xuhui Huang, Zhe Ma: ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
- Xuan Ma, Xiaoshan Yang, Junyu Gao, Changsheng Xu, Health Status Prediction with Local-Global Heterogeneous Behavior Graph, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2021
- Yi Huang, Xiaoshan Yang, Junyu Gao, Jitao Sang, Changsheng Xu, Knowledge-driven Egocentric Multimodal Activity Recognition, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2020
- Fan Qi, Xiaoshan Yang, Changsheng Xu, Emotion Knowledge Driven Video Highlight Detection, IEEE Transactions on Multimedia (TMM), 2020
- Junyu Gao, Xiaoshan Yang, Yingying Zhang, Changsheng Xu, Unsupervised Video Summarization via Relation-aware Assignment Learning, IEEE Transactions on Multimedia (TMM), 2020
- Wei Wang, Junyu Gao, Xiaoshan Yang, Changsheng Xu: Learning Coarse-to-Fine Graph Neural Networks for Video-Text Retrieval, IEEE Transactions on Multimedia (TMM), 2020
- Shan Zhang, Xiaoshan Yang, Yanxia Liu, Changsheng Xu, Asymmetric multi-stage CNNs for small-scale pedestrian detection, Neurocomputing, 2020
- Fan Qi, Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, Discriminative multimodal embedding for event classification, Neurocomputing, 2020
- Xuecheng Ning, Xiaoshan Yang, Changsheng Xu, Multi-hop Interactive Cross-Modal Retrieval, International Conference on Multimedia Modeling (MMM), 2020
- Yiming Li, Xiaoshan Yang, Changsheng Xu: Structured Neural Motifs: Scene Graph Parsing via Enhanced Context, International Conference on Multimedia Modeling (MMM), 2020
- Yingying Zhang, Junyu Gao, Xiaoshan Yang, Chang Liu, Yan Li, Changsheng Xu: Find Objects and Focus on Highlights: Mining Object Semantics for Video Highlight Detection via Graph Neural Networks, Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020
- Tingting Xie, Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, Ioannis Patras: Exploring feature representation and training strategies in temporal action localization. IEEE International Conference on Image Processing (ICIP), 2019
- Yi Huang, Xiaoshan Yang, Changsheng Xu: Time-Guided High-Order Attention Model of Longitudinal Heterogeneous Healthcare Data. Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2019
- Xiaoshan Yang, Changsheng Xu: Image Captioning by Asking Questions. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2019
- Weiming Zhang, Yi Huang, Wanting Yu, Xiaoshan Yang, Wei Wang, Jitao Sang: Multimodal attribute and feature embedding for activity recognition, Proceedings of the ACM Multimedia Asia, MM Asia, 2019
- Junyu Gao, Tianzhu Zhang, Xiaoshan Yang, Changsheng Xu: P2T: Part-to-Target Tracking via Deep Regression Learning. IEEE Trans. Image Processing (TIP) 27(6): 3074-3086 (2018)
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu: Deep-Structured Event Modeling for User-Generated Photos. IEEE Trans. Multimedia (TMM) 20(8): 2100-2113 (2018)
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu: Text2Video: An End-to-end Learning Framework for Expressing Text With Videos. IEEE Trans. Multimedia (TMM) 20(9): 2360-2370 (2018)
- Yifan Jiao, Zhetao Li, Shucheng Huang, Xiaoshan Yang, Bin Liu, Tianzhu Zhang: Three-Dimensional Attention-Based Deep Ranking Model for Video Highlight Detection. IEEE Trans. Multimedia (TMM) 20(10): 2693-2705 (2018)
- Yikun Sheng, Xiaoshan Yang, Changsheng Xu: A Standalone Demo for Quiz Game “Describe and Guess”. MIPR 2018: 206-207
- Yikun Sheng, Xiaoshan Yang, Xueliang Liu, Changsheng Xu: Attribute-Assisted Domain Transfer from Image to Sketch. MIPR 2018: 287-292
- Fan Qi, Xiaoshan Yang, Changsheng Xu: A Unified Framework for Multimodal Domain Adaptation. ACM Multimedia (MM), 2018: 429-437
- Junyu Gao, Tianzhu Zhang, Xiaoshan Yang, Changsheng Xu: Deep Relative Tracking. IEEE Trans. Image Processing (TIP) 26(4): 1845-1858 (2017)
- Yifan Jiao, Xiaoshan Yang, Tianzhu Zhang, Shucheng Huang, Changsheng Xu: Video Highlight Detection via Deep Ranking Modeling. PSIVT 2017: 28-39
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, Shuicheng Yan, M. Shamim Hossain, Ahmed Ghoneim: Deep Relative Attributes. IEEE Trans. Multimedia (TMM) 18(9): 1832-1842 (2016). Code
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu: Semantic Feature Mining for Video Event Understanding. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM) 12(4): 55:1-55:22 (2016)
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu: Abnormal Event Discovery in User Generated Photos. ACM Multimedia (MM) 2016: 47-51
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu: A new discriminative coding method for image classification. Multimedia System (MSJ) 21(2): 133-145 (2015)
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu: Cross-Domain Feature Learning in Multimedia. IEEE Trans. Multimedia (TMM) 17(1): 64-78 (2015). Code
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, M. Shamim Hossain: Automatic Visual Concept Learning for Social Event Understanding. IEEE Trans. Multimedia (TMM) 17(3): 346-358 (2015)
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, Ming-Hsuan Yang: Boosted Multifeature Learning for Cross-Domain Transfer. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM) 11(3): 35:1-35:18 (2015)
- Jianbing Shen, Xiaoshan Yang, Xuelong Li, Yunde Jia: Intrinsic Image Decomposition Using Optimization and User Scribbles. IEEE Trans. Cybernetics (TCYB) 43(2): 425-436 (2013)
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu: Locality discriminative coding for image classification. ICIMCS 2013: 52-55
- Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, Min Xu: Graph-Guided Fusion Penalty Based Sparse Coding for Image Classification. PCM 2013: 475-484
- Jianbing Shen, Xiaoshan Yang, Yunde Jia, Xuelong Li: Intrinsic images using optimization. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2011: 3481-3487. Code
Projects
- Youth Fund of NSFC: Knowledge-driven Video Understanding and Analysis
- Research Program of NLPR: Knowledge-driven Adversarial Video Generation
- CCF-Tencent Open Fund: Highlight Detection
- Cooperation Project of Migu: AI Service System for Video Annotation
- International Collaboration Project of NSFC: Personalized Health Management Based on Real-time Behavioral Data
Awards
| Year | Award | Category |
|---|---|---|
| 2018 | Best Patent Award | CCF-Tencent Open Fund |
| 2017 | Best Paper Award | ChinaMM |
| 2017 | Excellent Doctoral Dissertation | Chinese Academy of Sciences |
| 2016 | President Scholarship | Chinese Academy of Sciences |
Services
- ACM Multimedia 2018/2019/2020/2021 TPC member
- MM Asia 2019 Area Chair, ICPR 2020 Area Chair
- Journal/Conference Reviewer: IEEE TMM, IEEE TCSVT, PR, ACM TIST, ACM TOMM, Neurocomputing, MTAP and CVPR, ICCV, ACM MM