🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The good thing about having eye surgery is that you can fully sense the concept of depth perception from stereo cameras, pinhole cameras, and geometric distortion.

Absolutely thrilled teaching the "Intro to Machine Learning" ! Students' enthusiasm for learning is what makes teaching rewarding. I can't wait to see how far they'll go in this field! Huge thanks to David Fleet for being the best mentor!

Hi all, our research group has a collaboration opportunity available. We are seeking someone with expertise in wireless communication, if you are interested please send me a message.

There's a problem with 3D human pose & shape (HPS) estimation methods. You either get good 3D accuracy or good alignment with the image, but not both. Why? The current top methods use the wrong camera model. TokenHMR at #CVPR2024 analyzes the issue and presents a solution. (1/8)

radiovision.ai

What is the right benchmark for a 3D Egocentric Foundation model? We recently open-sourced a small, high quality egocentric benchmark consisting of 1) 3D surfaces 2) 3D objects. We released a simple 3D CNN baseline model called EVL: projectaria.com/research/efm3d/ Try to beat our model!

🎉🎉Excited to share that “CryoSPIN” has been accepted to #NeurIPS2024! Special thanks to my amazing collaborators and supervisors David Lindell, Marcus Brubaker, and David Fleet Paper: arxiv.org/abs/2406.10455 Webpage: shekshaa.github.io/semi-amortized… Code is also released! 🧵[1/7]

Please welcome Mehdy Dousty , our latest #SchmidtAIinSci Fellow! He works on gait analysis with Dr. Ervin Sejdić and David Fleet

Can you generate full body motion from **just** a head mounted camera? No, of course that's impossible! ... or is it? Check out HDM^2: hmdsquared.github.io Work by Vladimir Guzov and colleagues while interning at Meta:

📣 Two Postdoc or Research Associate positions at The Neuro's Personalized Medicine lab!! From two to three years with competitive salaries for working on advanced computational modeling of molecular and neuroimaging data in neurodegeneration. See neuropm-lab.com/open-positions…

Released by Reality Labs at Meta Research at #ECCV2024, Nymeria is a large-scale multimodal egocentric dataset for full-body motion understanding with potential applications in VR/MR headsets, smart glasses and more. More on this work + access to the dataset ➡️ go.fb.me/0znnvb

Point of view.

Lissajous curve table. Best geometry gif ever. [shorturl.at/XD0HR]

💡Paper 2: In-Ear System for Monitoring Lower Jaw Motion: A Novel Approach to Speech Intention Detection in Laryngectomy Patients - Published in IEEE Transactions on Biomedical Engineering - A good #rehabilitation or #assistive device must go beyond functionality - it needs to

Controllable video synthesis is critical to creating new tools for animation. Haven (Haiwen) Feng is graduating this year so keep your eye on him! He has a rapidly growing body of work that explores the properties of language, image, and video foundation models. Hire him if you can!

🎉It's officially time to introduce our second cohort of #SchmidtAIinSci Fellows!🎉 defygravitycampaign.utoronto.ca/news-and-stori…

🌟Three of our #SchmidtAIinSci Fellows are leveraging AI to accelerate research across various scientific domains, aiming to solve complex problems and drive innovation in their fields. We are excited to see how each of their companies shape the AI landscape! 🩺🌱🚶