🔥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

MoVi: A Large Multi-Purpose Human Motion and Video Dataset Demo: youtu.be/rXYV6xvd0j0. Website: biomotionlab.ca/movi/ BioMotionLab , @GunnarBlohm , Kording Lab 🦖 , Anne Thaler

This is EPIC!! It will go in history as one of the best #neurips talks of all times. ⁦Charles Isbell⁩ and colleagues 💜💙💚💛🧡❤️ on: Can’t Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise nips.cc/virtual/2020/p…

New article about two of my favorite things: meta-learning and Jax! This explores the complex meta-loss landscapes which merge from unrolled optimization procedures and shows why gradient based hyperparameter tuning can be hard even for simple problems. lukemetz.com/exploring-hype…

Spring has sprung! And with perfect timing for my new article, a gamedev's guide to springs: theorangeduck.com/page/spring-ro… Bit of an epic lockdown project for me; I applaud anyone who makes it all the way through! Hopefully it has some nice tricks and tidbits even for experience devs

BML members Adam Bebko and Anne Thaler are presenting new tools IEEE Virtual Reality. Here is the teaser for tomorrow's presentation on a tool that animates AMASS data in Unity. Poster session starts at 10am EST. youtube.com/watch?v=5uyAHu… VISTA @ YorkU, YorkU - Science

Adam Bebko and Anne Thaler gave a very well crafted tutorial on bmlTUX today IEEE Virtual Reality conference. If you missed it, check out the recording on YouTube: youtu.be/-1dh_U5RcKw. Starts at -4:56. VISTA @ YorkU YorkU - Science

Trailblazing research by then PhD candidate Anne Thaler & Professor & Canada Research Chair Nikolaus Troje examines virtual characters and walking style. VISTA @ YorkU Centre for Vision Research youtu.be/rns_E8WVuIU

Check out Michael Bronstein #ICLR2021 invited presentation, it’s gorgeous! slideslive.com/38956431

⏳ It's the final countdown! ⌛ #FarCry6

Turn marker based mocap point cloud into SMPL-X bodies; fuss-free. SOMA: Solving Optical Marker-Based MoCap Automatically - ICCV2021 Session 9 Code and supporting material online: soma.is.tue.mpg.de Perceiving Systems

If you jiggle a few black dots in a temporally correlated manner, it creates the illusion of not only form, but also curiosity and sentience

Finishing up this quick project with a short animation test. Kept the rig simple and only with controls I needed for this test #portraiture #blackbeauty #digitalart #blackpower #portrait #lighting #digitalhuman #animationtest

Signed!

"Pen & Paper Exercises in Machine Learning" -- probably the most interesting arXiv article I've seen in a while ☺️ 📝 arxiv.org/abs/2206.13446 Love it when exercises come with solutions. 👌 (Textbooks with exercises but w/o solutions are truly evil 😆).

honesty surprised this is not getting front page coverage or broad social media coverage in Canada

Our work in Two Minute Papers

What animal do you see in this video? With similar videos that isolate object movements, in a paper that just came out in #JNeurosci, Sophia Roberts sophie robert, Leslie Ungerleider, and I explored what brain regions process movement cues from objects. jneurosci.org/content/43/4/6…

Check out our blog on ZeroEGGS ubisoft.com/en-us/studio/l… UbisoftLaForge @Ubisoft Ubisoft Toronto

Animation quality is a difficult subject that I think we've not quite got to grips with yet as a community. My latest blog post shares some of my own thoughts on the subject. My hope is it can kickstart some discussions... or at least new dance moves! theorangeduck.com/page/animation…