Tarasha Khurana
I am an incoming Ph.D. student at The Robotics Institute, Carnegie Mellon University. Previously, during my Masters at RI, I was advised by Prof. Deva Ramanan on estimating and exploiting 3D scene geometry from single images to reason about occlusions and densify sparse depth input. I hold a B.E. degree in Computer Engineering from the University of Delhi and have had the fortune to work at amazing start-ups and labs - Argo AI, Staqu Technologies, CVML Lab (IIIT Delhi), Numerical Weather Prediction (IMD).

News
[07/21] My favorite work, Detecting Invisible People, was accepted to ICCV '21!
[04/21] I accepted CMU's PhD offer for Fall '21!
[07/20] The ECCV TAO Challenge is now live!
[07/20] TAO was accepted to ECCV '20 as a spotlight paper! Check out the manuscript.
[04/20] I'll be at Argo AI for the summer as a Research Intern!
[02/20] Our workshop titled, 'Object Tracking and its Many Guises' was accepted at ECCV 2020!
Recent Publications
Detecting Invisible People
Tarasha Khurana, Achal Dave, Deva Ramanan
International Conference on Computer Vision (ICCV), '21.
[arXiv] [project page]
TAO: A Large-Scale Benchmark for Tracking Any Object
Achal Dave, Tarasha Khurana, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan
European Conference on Computer Vision (ECCV) '20. Spotlight.
[arXiv] [project page] [workshop]
Exploiting Texture Cues for Clothing Parsing in Fashion Images
Tarasha Khurana, Kushagra Mahajan, Chetan Arora, Atul Rai
25th IEEE International Conference on Image Processing (ICIP) '18.
[pdf] [poster] [Xplore]
Pose Aware Fine Grained Visual Classification Using Pose Experts
Kushagra Mahajan, Tarasha Khurana, Ayush Chopra, Isha Gupta, Chetan Arora, Atul Rai
25th IEEE International Conference on Image Processing (ICIP) '18.
[pdf] [poster] [Xplore]


I also have experience in the following research topics - earth observation, audio-video lip reading, lung cancer prediction, table detection in documents, text recognition, adversarial example generation.