News / Latest News from the Lab

Radio interview on Face Recognition and Privacy on NPR

I participated today in an interesting discussion about face recognition technology and related privacy issues on National Public Radio with host Marty Moss-Coane and U Penn Law Professor Anita Allen. Thanks to the entire Radio Times crew at WHYY for the stimulating discussion.

A link to a recording of the live show can be found here

Workshop on Biologically Consistent Computer Vision @ CVPR

I’m helping to organize a workshop at the IEEE Computer Vision and Pattern Recognition conference this year in Colorado Springs on “Biologically Consistent Computer Vision.” We received an impressive array of submissions, and the workshop promises to be a good opportunity for those interested in biologically-inspired vision to come together and share ideas. See the workshop site for more details.

New Face Recognition Results

We recently presented new results using our large-scale feature search approach on the “Labeled Faces in the Wild” face recognition challenge set, yielding state-of-the-art performance.

For more information, see the corresponding paper.

GPU Technology Conference Talk

An online streaming version of a talk that Nicolas and I made in September at the GPU Technology Conference is now available here. In it, we talk about our work using GPUs to tackle large-scale face recognition problems.

Also, be sure to check out Nicolas’ talk on GPU Metaprogramming Techniques.

Google Research Award

We’re grateful and honored to have just been selected to receive a Google Research Award to help support our work with biologically-inspired vision systems. The Google Research Award program is part of Google’s broader effort to engage and support academic faculty pursuing research topics of mutual interest. We’re looking forward to working more closely with Google in the future. See the official announcement here.

New Paper: High-throughput Bio-inspired Computer Vision

In our new paper in PLoS Computational Biology, we describe our efforts to use GPU-accelerated high-throughput screening to find powerful new, biologically-inspired computer vision models.

Also check out the ResearchCast describing the work:

Finding a better way for computers to "see" from Cox Lab @ Rowland Institute on Vimeo.

New Paper: Rats as a model system for high level vision

In our new paper in PNAS, we present evidence that rats can perform high-level transformation-tolerant visual object recognition, an ability not traditionally ascribed to rodents. We believe that the availability of rats as a model system for high-level has great potential to accelerate our understanding of high-level vision, by providing a simpler, more accessible example system to study.

Top of the "Leader Board" in Real World Face Recognition

Our latest results on the “Labeled Faces in the Wild” face recognition were just posted to the official LFW website (http://vis-www.cs.umass.edu/lfw/results.html), where we currently have the best reported performance with our “V1-like” model. However, at the same time, we argue that even more realistic test sets are needed – to find out more, see our latest CVPR paper.

New GPU Cluster

Many thanks to NVIDIA for supplying GPU hardware for our formidable new GPU cluster, which features five GTX280s, five Tesla C1060s and two Tesla S1070 quad GPU 1U rack modules.

We’ll be making these systems available for the students of MIT’s “CUDA @ MIT” independent activities period, in order to help spread the joy of GPU to our friends down the river.