Research I am broadly interested in problems in computer vision and machine learning. My current research involves modeling and reasoning about human pose and action in images and video sequences using tools from machine learning and optimization.

Research

I am broadly interested in problems in computer vision and machine learning. My current research involves modeling and reasoning about human pose and action in images and video sequences using tools from machine learning and optimization.

Publications

Reconstructing 3D Human Pose from 2D Image Landmarks

Varun Ramakrishna, Takeo Kanade, Yaser Sheikh.

ECCV 2012.

Paper (ECCV ’12) Code Project

Conferences

Workshops

Mode Marginals: Expressing Uncertainty in MRFs via Diverse MBest Solutions.

Varun Ramakrishna, Dhruv Batra.

NIPS 2012 Workshop on Perturbations, Optimization, Statistics.

Paper (NIPS POS 2012)

Multi-Pose Multi-Target Tracking for Human Activity Understanding

Hamid Izadinia, Varun Ramakrishna, Kris Kitani, Daniel Huber.

WACV 2013.

Paper

Tracking Human Pose by Tracking Symmetric Parts

Varun Ramakrishna, Takeo Kanade, Yaser Sheikh.

CVPR 2013.

Paper