Hedvig Kjellström

I am a Professor in the Division of Robotics, Perception and Learning, KTH, and also affiliated with Swedish University of Agricultural Sciences, Silo AI, Swedish e-Science Research Centre, and Max Planck Institute for Intelligent Systems, Germany. A short bio is found here.

I do research in Computer Vision and Machine Learning. The general theme of my research is methods for enabling artificial agents to interpret human and animal behavior. As outlined in the Portfolio pages, these ideas are applied in the study of human aesthetic bodily expressions such as in music and dance, modeling and interpreting human communicative behavior, and the understanding of animal behavior and experiences. In order to accomplish this we develop methods for agents to perceive the world and build representations of it through vision.

I teach in the Bachelor program Engineering Mathematics and in the Master programs Machine Learning, Computer Science and Systems, Control and Robotics at KTH. My current courses are found below.

In my free time I play the double bass in different settings, more info here.

News

	On September 14, 2023, I featured in the UR documentary series Sverige Forskar and talked about our research on computer analysis of horse behavior. Here is the espisode (in Swedish).
	On April 21, 2023, I was interviewed in Swedish-speaking Finnish radio about AI and large language models like Chat-GPT. Here is the interview (in Swedish).
	On December 20, 2022, I appeared in Swedish television and talked about AI, creativity and what I think we should worry about. Here is the interview (in Swedish).
	NEW PAPER: Silvia Zuffi, Ylva Mellbin, Ci Li, Markus Hoeschle, Hedvig Kjellström, Senya Polikovsky, Elin Hernlund, and Michael J. Black. VAREN: Very accurate and realistic equine network. In IEEE Conference on Computer Vision and Pattern Recognition, 2024. Videos and code
	NEW PAPER: Marc Botet Colomer*, Pier Luigi Dovesi*, Theodoros Panagiotakopoulos, J. Frederico Carvalho, Linus Härenstam-Nielsen, Hossein Azizpour, Hedvig Kjellström, Daniel Cremers, and Matteo Poggi.  💀 To Adapt or Not to Adapt? Real-time adaptation for semantic segmentation. In IEEE International Conference on Computer Vision, 2023. (*Joint first authors) Videos and code
	NEW PAPER: Wenjie Yin, Ruibo Tu, Hang Yin, Danica Kragic, Hedvig Kjellström, and Mårten Björkman. Controllable motion synthesis and reconstruction with autoregressive diffusion models. In IEEE International Conference on Robot and Human Interactive Communication, 2023.