News:
- June 2024: Participated in the CVPR conference to present the papers accepted to the ABAW'24 workshop.
- December 2023: I will lead the student wellbeing task force formed at the Faculty of Science to prepare actionable plans for implementing the student wellbeing manifesto. The project will continue until the end of 2025.
- October 2023: I was thrilled to participate in Shonan Meeting on Conversational Qualities in Dyadic and Group Interactions. The discussions on conversational qualities were very productive and insightful.
- October 2023: Workshop on Bridging Social Sciences and AI for Understanding Child Behaviour at ICMI 2023 was a great success!
- October 2023: Our paper with Gizem Sogancioglu and Albert Ali Salah on using explainability to detect and mitigate bias in uni- and multi-modal prediction systems is presented at ICMI 2023.
- November 2022: Workshop on Bridging Social Sciences and AI for Understanding Child Behaviour @ ICMI'22 was a success!
- July 2022: The website for the Turkish Audio-Visual Bipolar Disorder Corpus is up!
- May 2022: I obtained my BKOw. The BKOw reflection (main portfolio document) is available here.
Earlier news:
- 2021: I collaborate in organizing ComParE 2021 Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates
- Our teams won two out of three ComParE challenges in 2020!
Heysem Kaya completed his PhD in computational paralinguistics and multimodal affective computing at the Computer Engineering Department, Bogaziçi University in 2015. He is an assistant professor affiliated with the Social and Affective Computing research group at the Department of Information and Computing Sciences, Utrecht University Science Faculty. He has published over 90 papers (2.6K citations, h-index=28the ) in international journals and conference proceedings. His works won six Computational Paralinguistics Challenge (ComParE) Awards at INTERSPEECH conferences between 2014 and 2020; as well as three ChaLearn Challenge Awards on video-based personality trait recognition (ICPR 2016) and explainable computer vision & job candidate screening (CVPR 2017) competitions. His team was the first runner up in video-based emotion recognition in the wild challenge (EmotiW 2015 at ICMI). His research interests include mixture model selection, speech processing, computational paralinguistics, and affective computing. He serves on runner-upthe editorial board of four journals including the flagship journal in affective computing, namely, IEEE Transactions on Affective Computing, as well as a reviewer in more than 30 journals including IEEE Trans. on {Affective Computing, Neural Networks and Learning Systems, Multimedia}, Image and Vision Computing, Computer Speech and Language, Neurocomputing, Speech Communication, Digital Signal Processing, and IEEE Signal Processing Letters.