Sijie Song  (宋思捷)

Institute of Computer Science and Technology
Peking University
No.5 Yiheyuan Road Haidian District, Beijing, P. R. China 100871

Ph.D. Candidate, Institute of Computer Science and Technology

Tel: +8610-82529531

Email: ssj940920 at pku.edu.cn

RESEARCH INTERESTS

Focused on digital image/video processing and computer vision, including

PUBLICATIONS

[1]Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng and Jiaying Liu. "Spatial-Temporal Attention Based LSTM Networks for 3D Action Recognition and Detection". IEEE Trans. on Image Processing (TIP), Vol.27, No.7, pp.3459-3471, July 2018.[Project] [pdf]

[2]Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng and Jiaying Liu. "Skeleton-Indexed Deep Multi-Modal Feature Learning for High Performance Human Action Recognition". Accepted by IEEE International Conference on Multimedia & Expo (ICME) 2018.

[3] Jiaying Liu, Yanghao Li, Sijie Song, Junliang Xing, Cuiling Lan, and Wenjun Zeng. "Multi-Modality Multi-Task Recurrent Neural Network for Online Action Detection", Accepted by IEEE Trans. on Circuit System for Video Technology (TCSVT), Jan. 2018.

[4]Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng and Jiaying Liu. "An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data". Proc. of AAAI Conference on Artificial Intelligence (AAAI), San Francisco, CA, U.S. Feb. 2017 (Oral, Full-Paper)[Project] [pdf]

[5] Chunhui Liu, Yueyu Hu, Yanghao Li, Sijie Song, and Jiaying Liu. "PKU-MMD: A Large Scale Benchmark for Skeleton-Based Human Action Understanding", Proc. of ACM Multimedia (ACM MM) Workshop, Silicon Valley, California, U.S., Oct. 2017.[Project] [pdf]

[6] Yueyu Hu, Chunhui Liu, Yanghao Li, Sijie Song and Jiaying Liu. "Temporal Perceptive Network for Skeleton-Based Action Recognition", Proc. of British Machine Vision Conference (BMVC), London, UK, Sep. 2017. [pdf]

[7] Shuai Yang, Sijie Song, Qikun Guo, and Jiaying Liu. "Facial Depth Map Enhancement via Neighbor Embedding", Proc. of International Conference on Pattern Reccognition (ICPR), Cancun, Mexico, Dec. 2016. [pdf]

[8] Sijie Song, Yanghao Li, Jiaying Liu and Zongming Guo. "Joint Sub-Band Based Neighbor Embedding for Image Super-Resolution", Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Shanghai, China, Mar. 2016. [Project][pdf]

[9] Shuai Yang, Jiaying Liu, Sijie Song, Mading Li and Zongming Guo. "Structure-Guided Image Completion via Regularity Statistics", Proc. of by IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Shanghai, China, Mar. 2016.[Project][pdf]

[10] Sijie Song, Yanghao Li, Zhihan Gao and Jiaying Liu. "Face Hallucination Based on Neighbor Embedding via Illumination Adaptation", Proc. of Asia Pacific Signal and Information Processing Association (APSIPA), Hong Kong, China, Dec. 2015.[Project][pdf]

[11] Mading Li, Wenhan Yang, Sijie Song and Zongming Guo. "Error Concealment with Multiscale Patch Clustering and Low-Rank Minimization", Proc. of Asia Pacific Signal and Information Processing Association (APSIPA), Hong Kong, China, Dec. 2015. [pdf]

PATENTS

[1] 基于多层次邻域嵌入的图像超分辨率重建方法及系统，专利申请人: 宋思捷、厉扬豪、刘家瑛、郭宗明，专利申请号:201610108841.3

[2] 深度图增强方法和深度图增强装置, 专利申请人: 杨帅、 刘家瑛、 宋思捷、 郭宗明， 专利申请号: 201611093936.9

[3] 人脸幻构方法和人脸幻构系统，专利申请人: 宋思捷、厉扬豪、刘家瑛、郭宗明，专利申请号:201510831521.6

[4] 一种基于稀疏表示的多层次图像风格的转换方法及装置，专利申请人: 宋思捷、杨撒博雅、刘家瑛、郭宗明，专利申请号:201510272143.2

[5] 基于偏移量的图像修复方法及装置，专利申请人：杨帅、刘家瑛、宋思捷、郭宗明，专利申请号：201510340991.20