Recent News

Dec 22, 2015 - AISTATS '16 Paper Accepted (Oral Presentation)
Work by Søren Hauberg, Oren Freifeld, Anders Boesen Lindbo Larsen, John W. Fisher III, and Lars Kai Hansen proposing "Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation" was accepted as an oral presentation to AISTATS '16.

Sept 08, 2015 - Two NIPS '15 papers accepted.
More details coming up soon.

Sept 01, 2015 - Two ICCV '15 papers accepted.
The paper "Semantically-Aware Aerial Reconstruction from Multi-Modal Data", by Randi Cabezas, Julian Straub and John W. Fisher III, and the paper "Highly-Expressive Spaces of Well-Behaved Transformations: Keeping it Simple", by Oren Freifeld, Søren Hauberg, Kayhan Batmanghelich and John W. Fisher III, were accepted to ICCV '15.

May 12, 2015 - A UAI '15 paper accepted.
Work by Liu, Peng, Ihler, and Fisher on "Estimating the Partition Function by Discriminance Sampling" was accepted to UAI '15.

May 06, 2015 - Fusion '15 paper accepted
Giorgos Papachristoudis' work "Efficient Information Planning in Gaussian MRFs" has been accepted to the 18th International Conference on Information Fusion (Fusion '15).

May 06, 2015 - ICML '15 paper accepted
Giorgos Papachristoudis' work "Adaptive Belief Propagation" has been accepted to the 32nd International Conference on Machine Learning (ICML '15).

Apr 30, 2015 - ICIP '15 paper accepted (Oral Presentation)
Work by Oren Freifeld, Yixin Li and John W. Fisher III proposing "A Fast Method for Inferring High-Quality Simply-Connected Superpixels" was accepted to ICIP '15.

Apr 09, 2015 - CVPR '15 Paper Accepted (Oral Presentation)
Work by Julian Straub, Trevor Campbell, Jonathan P. How and John W. Fisher III proposing two novel algorithms for "small-variance nonparametric clustering on the hypersphere" was accepted as an oral presentation at CVPR '15.

About SLI

Our group focuses on the analysis of complex, high-dimensional data. We combine elements of Bayesian inference, information theory, optimization, and physical sensor models to develop scalable algorithms with theoretical performance guarantees. Application areas include multi-modal data fusion, distributed inference under resource constraints, structural inference, resource management in sensor networks, and analysis of video, seismic volumes, and radar images.


Group Dinner - 05/20/2014
Left to Right: Oren Freifeld, Sue Zheng, Giorgos Papachristoudis, Guy Rosman, Christopher Dean, Jason Chang, Julian Straub, Randi Cabezas, John Fisher, Hossein Mobahi, Bonny Jain.