About me

I am an Assistant Professor in the College of Information and Computer Sciences at the University of Massachusetts, Amherst and the co-director of the Computer Vision Lab. Prior to this, I spent three years as a Research Assistant Professor at TTI Chicago, a philanthropically endowed academic computer science institute in the University of Chicago campus. I obtained my Ph.D. under the supervision of Jitendra Malik from the University of California at Berkeley in 2011, and a B.Tech in Computer Science and Engineering from IIT Kanpur in 2006. In the past I have enjoyed working at Google, INRIA LEAR group, Microsoft Research India, the CLSP center at Johns Hopkins University and Oxford University. Here is a detailed CV.

My research focusses on computer vision with a particular emphasis on algorithms for high-level recognition. My goal is enable cheap and robust sensing of the visual world using cameras powered by computer vision. For an overview of my research take a look at my recent publications and projects. I am also on Google scholar.

Computer science department rankings: http://csrankings.org.

Recent news

12/17 I will serve as an area chair for CVPR 2018.
10/17 Invited talk at the Manifold Learning Workshop @ ICCV 17.
7/17 Dark ecology project funded by NSF. Link to the press release.
7/17 Upcoming papers and recent preprints:
+ 2 papers at 3DV, 3 papers at BMVC 17, 1 at ICCV 17 (see publications)
+ Bilinear CNNs PAMI preprint, arXiv v6, Jun 2017 (updated accuracy)
+ 3D Shape Segmentation with Projective Convolutional Networks, CVPR 17 (oral presentation)
+ 3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks, arXiv, July 17
4/17 Department colloquium speaker at RIT and UoR.
9/16 Teaching Computer Vision @ UMass
6/16 Received NSF grant for language-based understanding of textures, and a gift from Facebook.
4/16New arXiv preprints (Cross quality distillation, Inference with perturb-MAP)
3/16Recent papers (WACV 16, CVPR 16)
1/16 Teaching Intro to Computer Vision (370/370HH) @ UMass
1/16 Journal paper on texture recognition using CNNs appears on IJCV online (open access)
1/16 Talk slides for the bilinear CNN ICCV 2015 oral. Here is a longer version of the talk I gave at MIT, Berkeley, Microsoft Research, Google and FAIR recently.
11/15 We are organizing the first New England Computer Vision Workshop on November 20, 2015
9/15 One oral and one poster accepted to ICCV 2015 [code available]
9/15 Code for texture recognition with deep filter banks (CVPR 15 paper) released on GitHub
8/15 I will serve as an area chair for CVPR 2016
5/15 Fine-Grained Visual Categorization (FGVC) workshop at CVPR 2015
5/15 Arxiv paper on fine-grained recognition using bilinear models
3/15 One paper accepted as an oral at CVPR 2015
1/15 Teaching Machine Learning @ Umass
1/15 Awarded WACV 2015 Best Paper for the Vision and Learning session


Coursework: Tutorials: Workshops:


Advisees: Past student collaborators:


Here is a wordle of my research statement.

I occasionally draw and paint.