skip to content

Department of Computer Science and Technology

  • Affiliated Researcher
  • Lecturer, University of Leicester

I am currently a Lecturer (Assistant Professor) at the University of Leicester. I am also an affiliated/visiting researcher at the Department of Computer Science and Technology, University of Cambridge. I was a Research Associate worked with Prof. Hatice Gunes from 09/2020 at the University of Cambridge. Prior to that, I obtained my PhD degree at the University of Nottingham, funded by Horizon CDT, under Prof Michel Valstar and Prof Alan Johnston's supervision.


Siyang's research interests include:

Affective Computing

Human-computer Interaction

Computer Vision

Machine Learning

Graph Representation Learning


Recent publications:

[1] Song, Siyang, Zilong Shao, Shashank Jaiswal, Linlin Shen, Michel Valstar, and Hatice Gunes. "Learning Person-specific Cognition from Facial Reactions for Automatic Personality Recognition." IEEE Transactions on Affective Computing (2022).

[2] Luo, Cheng*, Siyang Song*, Weicheng Xie, Linlin Shen, and Hatice Gunes. "Learning multi-dimensional edge feature-based au relation graph for facial action unit recognition." IJCAI 2022 (Equal first author)

[3] Shao, Zilong, Siyang Song*, Shashank Jaiswal, Linlin Shen*, Michel Valstar, and Hatice Gunes. "Personality Recognition by Modelling Person-specific Cognitive Processes using Graph Representation." 29th ACM International Conference on Multimedia (2021). (Corresponding author)

[4]Song, Siyang, Shashank Jaiswal, Linlin Shen, and Michel Valstar. "Spectral representation of behaviour primitives for depression analysis." IEEE Transactions on Affective Computing (2020).

[5] Song, Siyang, Shashank Jaiswal, Enrique Sanchez, Georgios Tzimiropoulos, Linlin Shen, and Michel Valstar. "Self-supervised Learning of Person-specific Facial Dynamics for Automatic Personality Recognition." IEEE Transactions on Affective Computing (2021).

[6] Song, Siyang, Linlin Shen, and Michel Valstar. "Human behaviour-based automatic depression analysis using hand-crafted statistics and deep learned spectral features." In 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 158-165. IEEE, 2018.

Contact Details