Teaching an AI to Detect Key Actors in Multi-person Videos

Research, cuDNN, Higher Education / Academia, Image Recognition, Machine Learning & Artificial Intelligence, Media & Entertainment, Tesla, Video Processing

Nadeem Mohammad, posted Jul 06 2016

Researchers from Google and Stanford have taught their computer vision model to detect the most important person in a multi-person video scene – for example, who the shooter is in a basketball game which typically contains dozens or hundreds of people in a scene. Using 20 Tesla K40 GPUs and the cuDNN-accelerated Tensorflow deep learning

Read more

Getting to know the new HDR

GameWorks, HDR

Evan Hart, posted Jul 05 2016

We’ve already started with teaser posts about HDR on this blog both here and here. Now that we’ve gotten through the madness of launching a new product, it is time to go through a more detailed set of information on the how, why, and what of HDR. This post kicks off a whole series of blog posts on HDR and color evolutions for

Read more

New Deep Learning Method Enhances Your Selfies

Research, cuDNN, Higher Education / Academia, Image Processing, Machine Learning & Artificial Intelligence, Media & Entertainment, Tesla, Video Processing

Nadeem Mohammad, posted Jul 05 2016

Researchers from Adobe Research and The Chinese University of Hong Kong created an algorithm that automatically separates subjects from their backgrounds so you can easily replace the background and apply filters to the subject. Their research paper mentions there are good user-guided tools that support manually creating masks to separate subjects from the background, but

Read more

Facebook and CUDA Accelerate Deep Learning Research

News, Research, CUDA, cuDNN, Development Tools & Libraries, Image Processing, Internet / Communications, Machine Learning & Artificial Intelligence, Tesla

Nadeem Mohammad, posted Jun 30 2016

Last Thursday at the International Conference on Machine Learning (ICML) in New York, Facebook announced a new piece of open source software aimed at streamlining and accelerating deep learning research. The software, named Torchnet, provides developers with a consistent set of widely used  deep learning functions and utilities. Torchnet allows developers to write code in

Read more

Pinterest Introduces the Future of Visual Search

News, Research, Caffe, Cloud, GeForce, Image Processing, Internet / Communications, Machine Learning & Artificial Intelligence

Nadeem Mohammad, posted Jun 30 2016

The popular social photo sharing site is adding the ability for people to take a photo of things in the real-world and get recommendations for similar products on Pinterest. For example, If you take a photo of a room with a purse and a lamp on a table that you like, Pinterest will show you

Read more