Sijie Song (宋思捷)

Ph.D. student @ PKU
ssj940920 AT pku.edu.cn

A CSer, also a dancer.

About Me

I am currently a fifth-year Ph.D candidate with Wangxuan Institute of Computer Technology, Peking University, under the supervision of Prof. Zongming Guo and Prof. Jiaying Liu at STRUCT. My research interests include computer vision, image processing.

Experience
  • 2016.9~2021.7 (expected)   Ph.D. student, WICT, Peking University
  • 2012.9~2016.7    B.S. major in Computer Science, EECS, Peking University
  • 2014.9~2016.7    B.E. minor in Economics, NSD, Peking University
  • Selected Publication   *For full publication list, please visit [google scholar]

    Modality Compensation Network: Cross-Modal Adaptation for Action Recognition

    Sijie Song, Jiaying Liu, Yanghao Li, Zongming Guo

    IEEE Trans. on Image Processing (TIP), Vol.29, pp. 3957-3969, Jan. 2020.

    [Project] [Paper]

    Unpaired Person Image Generation with Semantic Parsing Transformation

    Sijie Song, Wei Zhang, Jiaying Liu, Zongming Guo, Tao Mei

    Accepted to IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), Apr. 2020.

    Unsupervised Person Image Generation with Semantic Parsing Transformation

    Sijie Song, Wei Zhang, Jiaying Liu, Tao Mei

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 (Oral).

    [Project] [Paper] [Supp] [Code]

    Temporal Bilinear Networks for Video Action Recognition

    Yanghao Li, Sijie Song, Yuqi Li, and Jiaying Liu
    AAAI Conference on Artificial Intelligence (AAAI), 2019 (Oral/Full)

    [Project] [Paper]

    Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection

    Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng, and Jiaying Liu
    IEEE Trans. on Image Processing (TIP), Vol.27, No.7, pp.3459-3471, July 2018.

    [Project] [Paper]

    Multi-Modality Multi-Task Recurrent Neural Network for Online Action Detection

    Jiaying Liu, Yanghao Li, Sijie Song, Junliang Xing, Cuiling Lan, and Wenjun Zeng
    IEEE Trans. on Circuit System for Video Technology (TCSVT), Vol.29, No.9, pp.2667-2682, Sep. 2019.

    [Project] [Paper]

    Skeleton-Indexed Deep Multi-Modal Feature Learning for High Performance Human Action Recognition

    Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng and Jiaying Liu.
    IEEE International Conference on Multimedia & Expo (ICME), 2018.

    [Paper]

    PKU-MMD: A Large Scale Benchmark for Skeleton-Based Human Action Understanding

    Chunhui Liu, Yueyu Hu, Yanghao Li, Sijie Song, and Jiaying Liu.
    ACM Multimedia (ACM MM) Workshop 2017

    A Benchmark Dataset and Comparison Study for Multi-Modal Human Action Analytics

    Jiaying Liu, Sijie Song, Chunhui Liu, Yanghao Li, Yueyu Hu
    ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Vol.16, No.2, pp.1551-6857, May 2020.

    [Dataset]

    An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data

    Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng, Jiaying Liu
    AAAI Conference on Artificial Intelligence (AAAI), 2017 (Oral/Full)

    [Project] [Paper] [Slides]

    Honors and Awards
  • Google Grace Hopper Celebration Travel Grant Recipient, 2018
  • Huawei Scholarship, EECS, Peking University, 2017
  • Wangxuan Scholarship, ICST, Peking University, 2016
  • Google Anita Borg Memorial Scholarship: Asia Pacific, 2016
  • Outstanding Graduate, Peking University, 2016
  • Top 10 Distinguished Papers, EECS, Peking University, 2016
  • Lee Wai Wing Scholarship, Peking University, 2015
  • Guanghua Scholarship, Peking University, 2014
  • Merit Student Award, Peking University, 2013, 2015, 2017, 2018
  • Professional Activities
  • Reviewer for TIP, TIFS, TCSVT, TMM, TOMM