Please join us at the 1st #Workshop, #Benchmark, and #Challenge on Human Trajectory and Pose Dynamics Forecasting in the Wild, ICCV2021. We have an amazing lineup of organizers & speakers. somof.stanford.edu Workshop: somof.stanford.edu/workshops/iccv… Paper: arxiv.org/pdf/2104.04029…

A desperate call from Iranian international students who say they remain in a state of limbo as they wait for their spouses open work permits to be approved. Melissa Nakhavoly toronto.citynews.ca/video/2023/03/…

Happy that this paper is finally out: "Ambient Monitoring of Gait and Machine Learning Models for Dynamic and Short-Term Falls Risk Assessment in People With Dementia" IEEE Engineering Medicine and Biology Society Journal of Biomedical and Health Informatics (JBHI) ieeexplore.ieee.org/document/10102…

Some of our group members presenting their work at #ICAIR2023 and clearly enjoying talking about their research 😃

It was a pleasure attending the #ICAIR2023 conference and having the great opportunity to connect with professionals on the forefront of healthcare science! Thanks @MilosRPopovic and all the ICAIR organizing members for such an informative and engaging event! KITE Research Institute

We (Ehsan Adeli, Itir Onal Ertugrul, R. James Cotton, & I) are organizing a Workshop on Ambient Intelligence for HealthCare as part of MICCAI Society #MICCAI2023. Consider submitting if you work in this area (deadline Jun 25) and come by for the amazing keynote speakers ami4hc.stanford.edu

Delighted that MotionAGFormer has been accepted at #wacv2024. We achieve SOTA 3D human pose estimation on Human3.6M and MPI-INF-3DHP. paper: arxiv.org/abs/2310.16288 code: github.com/TaatiTeam/Moti… Nice work by KITE Trainees Soroush Mehraban Biomedical Engineering @ University of Toronto and Vida Adeli U of T Department of Computer Science

Just posted a YouTube video reviewing the paper. Check that out if interested: youtu.be/iyLhxPjwBuQ

This simple pytorch trick will cut in half your GPU memory use / double your batch size (for real). Instead of adding losses and then computing backward, it's better to compute the backward on each loss (which frees the computational graph). Results will be exactly identical

📌 Our CARE-PD poster will be presented on Dec 3, 1–4pm CST at the Mexico City poster session (#NeurIPS2025). Feel free to stop by and chat if you’re around. Project page: neurips2025.care-pd.ca

‼️ Code, model weights, dataset now available! ‼️ We built a new way to take any video and transform it into a different artistic style (think: making your home movie look like a Van Gogh painting) while keeping everything else intact. The big problem? There's almost no

POWERFUL PROTESTS: Video from inside Iran shows massive crowds filling the streets in protest against the hardline Islamist government, despite the internet crackdown in the country. The protests have grown in recent days as frustrated Iranians speak out against rampant

#DigitalBlackoutIran

#FreeIran2026 #DigitalBlackoutIran

Today I woke up to reports of ~12,000 lives lost in Iran in the past few days. I can’t begin to process that number. Here’s a simulation of just 6,000 particles to visualize it. Thinking of my Iranian friends/colleagues, hope you and your families are safe. #DigitalBlackoutIran

Come by our posters if you're attending #WACV2026. 1) FastHMR: Fast 3D Human Mesh Recovery, Tue 10:45–12:15 poster #89 2) GAITGen: Generative Gait Synthesis and Analysis Mon 10:45–12:30 poster #22 3) STARS (action recognition) Sunday 4:00-5:45 poster #137