srikumar ramalingam

Associate Professor at Univ of Utah, computer vision and machine learning researcher

[Suhail Mohammed @msuhail153]

Our paper "Generalizable Patch-Based Neural Rendering" was accepted as an oral at #ECCV2022.
Joint work with @_machc, Leonid Sigal and @kiamada.
Project Page: https://t.co/ZmxuKa9X0h
1/2🧵

[Carlos Esteves @_machc]

We will present our poster on Implicit-PDFs at #ICML2021 tonight 12-2am ET.

Check out the talk here: https://t.co/j8SSuJ9Q57.

For all details, including code and demo colab, visit https://t.co/KBpBentOjU.

With @kmurmurs, @jampani_varun, @srikumarRam, @kiamada.

[Ameesh Makadia @kiamada]

To make 3D pose estimation useful in practice it must deal with uncertainties due to symmetry or occlusion.

Our latest work, ImplicitPDF, predicts arbitrarily complex distributions over pose using an implicit representation of SO(3). #ICML2021

https://t.co/FTjiXCDWpO

[Andrej Karpathy @karpathy]

Discovering (paradoxically late in life) that I get more out of textbooks than books and that I don’t have to stop buying them just because I’m out of school. Good reading list pointers: https://t.co/ZDaqr3YQbW

[Suresh Venkatasubramanian (mostly in the sky now) @geomblog]

It's a pity they didn't have a preprint that people could critique BEFORE it got into print 🤔

[Suresh Venkatasubramanian (mostly in the sky now) @geomblog]

My quote about medicines got a little mangled I think but overall it's all good. What I was trying to say that we often demand responsibility and guidance from entities that release advanced tech, like with drug companies and medicines. https://t.co/bSDPmPJmuM

[University of Utah @UUtah]

Pioneer Day has us thinking about the U's legacy and rich history of developing the foundations for computer graphics and much of today's technology. #PioneerDay #Daysof47

https://t.co/ozbN2h6246 💻

[srikumar ramalingam @srikumarRam]

@thserra Thanks Thiago!

[Prafulla Dhariwal @prafdhar]

Code for the Glow demo is now on github! Use the pre-trained model to create manipulation vectors from your own labelled dataset (eg: changing hair color to red). You can also run the demo locally, go make your own smiling videos!
https://t.co/kLTURsLX0d

[srikumar ramalingam @srikumarRam]

Semantic boundaries can be extremely beneficial for accurate localization

https://t.co/0t8neSY8yg

Joint work with Xin Yu, Sagar Chaturvedi, Chen Feng, Clinton Fernandes, Yuichi Taguchi and Teng-Yok Lee. The paper will be presented in IROS 2018 in Madrid
https://t.co/E9B4fsaDVw

[Thiago Serra (@thserra.bsky.social) @thserra]

The #icml2018 camera-ready version of the Bounding & Counting paper is on arxiv: https://t.co/3gG7bfnb3O

We investigate in theory and practice what piecewise-linear functions can be modeled with different neural networks.

I am presenting a poster next week at #mip2018 #orms

[srikumar ramalingam @srikumarRam]

We are looking for strong Ph.D. students in vision, graphics, and machine learning
https://t.co/q4rd82NHWE