Homepage


About Me:
I'm a fifth year graduate student in the MS/PhD programme in Computer Science, University of Massachusetts. My research interests are in Computer Vision and Machine Learning, focusing on fine-grained recognition, face recognition and deep learning. I am co-advised by Prof. Erik Learned-Miller and Prof. Subhransu Maji at the UMass Vision Lab. For my synthesis project, I have worked with Prof. Dan Sheldon on ecological computing.

I maintain the website for FDDB - a benchmark for detecting faces. I have been a reviewer for CVPR and the journals TPAMI and CVIU. At UMass I help organize the Machine Learning and Friends Lunch (MLFL) seminar series. Earlier, I was involved in GRiD, a multidisciplinary graduate student organisation for data science.

I have spent two happy summers in 2017 and 2014 interning at The Mathworks Inc. with the Computer Vision Toolbox team.

In the past I had worked on scene text detection and handwriting recognition at the Indian Statistical Institute, Kolkata. My mentors there had been Profs U Bhattacharya and SK Parui.
Contact:
arunirc[at]cs.umass.edu
Computer Science Building, Rm 256 (2)
140 Governors Drive
Amherst, MA 01003.
News:
  • One paper @ CVPR 2018 (second author)
  • Reviewer for CVPR 2018.
  • Attending NIPS 2017.
  • Summer internship with Mathworks, May-August 2017.

Resume:
Online resume (research) [pdf].
Publications:

Grad:
  • The Best of Both Worlds: Combining CNNs and geometric constraints for hierarchichal motion segmentation.
    Pia Bideau, Aruni RoyChowdhury, Rakesh Menon, Erik Learned-Miller.
    Computer Vision and Pattern Recognition (CVPR), 2018.
    [project page]
  • Reducing Duplicate Filters in Deep Neural Networks.
    Aruni RoyChowdhury, Prakhar Sharma and Erik Learned-Miller.
    NIPS workshop on Deep Learning: Bridging Theory and Practice (DLTP), 2017.
    [paper]
  • Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition.
    Tsung-Yu Lin, Aruni RoyChowdhury and Subhransu Maji.
    IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
    [project page]
  • Radar Analysis of Bird Migration.
    Kevin Winner, Garrett Bernstein, Andrew Farnsworth, Aruni Roy Chowdhury and Dan Sheldon.
    International Conference on Computational Sustainability (Comp-Sust), 2016.
  • Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery.
    Aruni RoyChowdhury, Daniel Sheldon, Subhransu Maji and Erik Learned-Miller.
    CVPR workshop on Perception Beyond the Visual Spectrum (PBVS), 2016.
    [paper]
  • One-to-many face recognition with bilinear CNNs.
    Aruni RoyChowdhury, Tsung-Yu Lin, Subhransu Maji and Erik Learned-Miller.
    Winter Conference on Applications of Computer Vision (WACV), 2016.
    [paper] [slides] [arxiv-old]
  • Bilinear CNN Models for Fine-grained Visual Recognition.
    Tsung-Yu Lin, Aruni RoyChowdhury and Subhransu Maji.
    International Conference on Computer Vision (ICCV), 2015.
    [project page]

Undergrad:
  • Stroke level user-adaptation for stroke order free online handwriting recognition.
    D Dutta, A Roy Chowdhury, U Bhattacharya, SK Parui. International Conference on Frontiers in Handwriting Recognition (ICFHR), 2014.
  • Scene text detection using sparse stroke information and MLP.
    A Roy Chowdhury, U Bhattacharya, SK Parui. International Conference on Pattern Recognition (ICPR), 2012.
  • Building a Personal Handwriting Recognizer on an Android Device.
    D Dutta, A Roy Chowdhury, U Bhattacharya, SK Parui. International Conference on Frontiers in Handwriting Recognition (ICFHR), 2012.
  • Text detection of two major Indian scripts in natural scene images.
    A Roy Chowdhury, U Bhattacharya, SK Parui. ICDAR Workshop on Camera-Based Document Analysis and Recognition (CBDAR), 2011.