Guanyu Hu: "Advancing Affective Computing from Robust Perception to Interpretable and Fair Reasoning"

HIIT Special Seminars
This talk is part of the HIIT Special Seminar series. The talks in this series are provided by candidates who have applied to our HIIT Fellowship recruitment call and are highly considered for the position. All talks are virtual, open to the public, and recorded for the future
HIIT Special Seminar

When

–

Where

Online

Event language(s)

English
Join via zoom

This talk can be viewed via zoom. (Note: this talk will be recorded)

Title:
Advancing Affective Computing from Robust Perception to Interpretable and Fair Reasoning

Abstract:
Affective computing has achieved strong predictive performance, but real-world deployment requires more than robust recognition under unconstrained conditions. It also calls for models whose reasoning process is more interpretable and whose behaviour can be assessed more fairly across tasks and populations. This talk introduces how affective computing can move from robust perception in the wild toward interpretable and fair reasoning through cognitively grounded representations, causal modeling, and principled evaluation protocols, advancing toward systems that are more transparent, more trustworthy, and better suited to practical deployment.

Bio: Guanyu Hu is a recent graduate from Xi’an Jiaotong University, advised by Prof. Xinyu Yang. He is currently a Research Associate at Queen Mary University of London for Prof. Dimitrios Kollias. His publications include papers in top venues such as ACM MM, AAAI, CVPR, and INTERSPEECH. His work has received the Best Reviewed Paper award at IEEE FG and has attracted 559 Google Scholar citations with an h-index of 11.

  • Updated:
  • Published:
Share
URL copied!