journal club
Upcoming speakers, past sessions, and the organizing team.
Paper discussions and guest talks on computer vision and machine learning, with a focus on human motion and health applications. Run by Dr. Babak Taati's group at the University of Toronto, KITE, and the Vector Institute since 2019.
Weekly email with the next speaker, Zoom link and passcode.
Upcoming speakers
ActDiff-VC is a generative video compression framework that pairs active sampling with conditional video diffusion. Rather than transmitting information for every frame, it adaptively selects keyframes from scene dynamics and represents motion with a compact set of point trajectories, and a conditional diffusion decoder reconstructs the video from these sparse signals. On standard benchmarks it reaches up to 64.6% bitrate reduction at comparable perceptual quality relative to strong learned codecs.
Organizing team
Kimia Shaban
Runs the journal club: sets the schedule, invites speakers, and keeps this page up to date. Works on computer vision and vision-language models.
Babak Taati
Holds the Barbara G. Stymiest Chair in Rehabilitation Technology Research and leads the KITE Aging Team. Hosts the journal club and keeps the long-term archive.
Vida Adeli
Works on generative models for 3D human motion, animation, and clinical gait analysis. Organized the journal club before Kimia.
Past sessions
Sessions from 2019 to 2024 are listed on Babak Taati's site.