Vishnu Boddeti

Principal Investigator
Twitter
GitHub
Google Scholar
Email
firstnameobfuscate@msu.edu

I’m an Assistant Professor in the Computer Science Department at Michigan State University. My research is focused at the intersection of Computer Vision, Biometrics and Machine Learning. Specifically, I build computational models for analyzing human attributes, behaviors and interactions from data.

I received my bachelor’s degree from the Indian Institute of Technology, Madras and my PhD from Carnegie Mellon University, advised by Vijayakumar Bhgavatula. Following my PhD I was a Postdoctoral Fellow in the Robotics Institute at Carnegie Mellon University where I worked with Takeo Kanade.

Papers

Constrained Sampling: Optimum Reconstruction in Subspace with Minimax Regret Constraint

RankGAN: A Maximum Margin Ranking GAN for Generating Faces

NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search

Secure Face Matching Using Fully Homomorphic Encryption

Perturbative Neural Networks

On the Intrinsic Dimensionality of Face Representation

Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator for Static Video Surveillance

Efficient K-Shot Learning with Regularized Deep Networks

On the Capacity of Face Representation

Local Binary Convolutional Neural Networks

Face Alignment Robust to Pose, Expressions and Occlusions

Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking

Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

Gesture-based Bootstrapping for Egocentric Hand Segmentation

In Teacher We Trust: Learning Compressed Models for Pedestrian Detection

Stacked correlation filters for biometric verification.

Probabilistic deformation models for challenging periocular image verification.

Zero-Aliasing Correlation Filters for Object Recognition.

Learning scene-specific pedestrian detectors without real data.

Face Alignment Refinement.

3D Pose-by-Detection of Vehicles via Discriminatively Reduced Ensembles of Correlation Filters.

Maximum margin vector correlation filter.

Maximum-margin coupled mappings for cross-domain matching.

A framework for binding and retrieving class-specific information to and from image patterns using correlation filters.

Correlation Filters for Object Alignment.

Maximum Margin Correlation Filter: A new approach for localization and classification.

Coupled marginal fisher analysis for low-resolution face recognition.

Rainmon: an integrated approach to mining bursty timeseries monitoring data.

Matching highly non-ideal ocular images: An information fusion approach.

Improved Iris Segmentation based on Local Texture Statistics.

A comparative evaluation of iris and ocular recognition methods on challenging ocular images.

Extended-depth-of-field iris recognition using unrestored wavefront-coded imagery.

A biometric key-binding and template protection framework using correlation filters.

Extended Depth of Field Iris Recognition with Correlation Filters.