Anand Mishra, PhD
CDS-317, Department of Computational and Data Sciences
Indian Institute of Science Bangalore
Bengaluru - 560012 (KA), India

I am a Postdoctoral Fellow at Indian Institute of Science Bangalore. Here, I am hosted by Dr. Partha Pratim Talukdar and Dr. Venkatesh Babu at Machine and Langauge Learning (MALL) lab. Prior to this, I worked under supervision of Prof. C. V. Jawahar and Dr. Karteek Alahari for my PhD dissertation on scene text understanding at IIIT Hyderabad. At IIIT, I was a reciptent of Microsoft Research India PhD fellowship 2012 and XRCI best doctoral dissertation award: first runner up 2015.

My current research interest spans Computer Vision and Knowledge Graphs. To be specific, I focus on using structured knoweledge bases for addressing various Computer Vision tasks.

Prior to joining IIIT-H for my PhD, I obtained my master's degree from Birla Institute of Technology, Mesra and undergraduate degree from Guru Ghashidas university Bilaspur (now a central university).

Email  /  CV  /  Google Scholar /  DBLP

NOTE: I am currently not offering any internship position. Hence, no email regarding this will be entertained. I apologize.

News

  • [March 2019]: I will be serving as a program committee member for ICDAR 2019.
  • [February 2019]: I will be serving as a reviewer for ICCV 2019.
  • [February 2019] Offered a lecture on Graph Representation Learning in Deep Learning for Computer Vision course at IISc Banglore.
  • [January 2019]: I will be serving as a program committee member for IJCAI 2019.
  • [December 2018]: I am attending AAAI 2019. My travel is supported by gift of USD 3000 by Google to Indian Institute of Science. Thank you Google.
  • [November 2018]: I am serving as a program committee member for Workshop on Document Analysis and Recognition (DAR) 2018. (to be held as part of ICVGIP 2018)
  • [November 2018]: Our work on "Knowledge-Aware Visual Question Answering" got accepted in AAAI 2019 (acceptance rate = 16 %)
  • [October 2018]: My solo author paper on deep heterogeneous metric learning got accepted for publication at
    International Journal of Multimedia Information Retrieval (IJMIR). This paper addresses the problem of matching cartoon and real faces.
  • [September 2018]: Our paper on deep metric learning got accepted at ACCV 2018. Pre-print will be available soon!
  • [September 2018]: I will be attending Amazon Research Day on September 28.
  • [July 2018]: I will be co-teaching an undergrad introductory course on Algorithms and Programming at IISc Bangalore. [Link]

Selected Publications

Journals

  • DHFML: deep heterogeneous feature metric learning for matching photograph and cartoon pairs (NEW)
    Anand Mishra
    pages: 1-8, International Journal of Multimedia Information Retrieval 2018
    [Link][bibtex]
  • Unsupervised refinement of color and stroke features for text binarization
    Anand Mishra, Karteek Alhari and C. V. Jawahar
    Volume 20:105–121, International Journal on Document Analysis and Recognition 2017
    [PDF][bibtex]
  • Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues
    Anand Mishra, Karteek Alhari and C. V. Jawahar
    Volume 145: 30-42, Computer Vision and Image Understanding 2016
    [PDF][bibtex]

Conference Papers

  • KVQA: Knowledge-aware Visual Question Answering (NEW)
    Sanket Shah*, Anand Mishra*, Naganand Yadati and Partha Pratim Taulkdar
    (*: equal contribution) AAAI 2019. (acceptance rate: 16.1%)
    [Paper (arXiv):comming soon] [bibtex] [Project page]
  • Deep Embedding using Bayesian Risk Minimization with Application to Sketch Recognition (NEW)
    Anand Mishra,and Ajeet Kumar Singh
    ACCV, 2018. (acceptance rate: 28%)
    [Paper (arXiv)] [bibtex]
  • IIIT-CFW: A Benchmark database of Cartoon Faces in the Wild
    Ashutosh Mishra, Shyam N. Roy, Anand Mishra,and C. V. Jawahar
    ECCVW, 2016. (Oral)
    [PDF] [bibtex][ IIIT-CFW dataset]
  • A Simple and Effective method for Script Identification in the Wild
    Ajeet Kumar Singh, Anand Mishra, Pranav Dabaral and C. V. Jawahar
    DAS, 2016.
    [Paper] [bibtex]
  • Scene Text Recognition and Retrieval for Large Lexicons
    Udit Roy, Anand Mishra, Karteek Alhari and C. V. Jawahar
    ACCV, 2014.
    [Paper] [bibtex]
  • Image Retrieval using Textual Cues
    Anand Mishra, Karteek Alhari and C. V. Jawahar
    ICCV, 2013.
    [Paper] [bibtex]
  • Whole is Greater than Sum of Parts: Recognizing Scene Text Words
    Vibhor Goel, Anand Mishra, Karteek Alhari and C. V. Jawahar
    ICDAR, 2013.
    [Paper] [bibtex]
  • Scene Text Recognition using Higher Order Language Priors
    Anand Mishra, Karteek Alhari and C. V. Jawahar
    BMVC 2012. (Oral)
    [Paper] [bibtex] [ IIIT-5K Word dataset]
  • Top-down and Bottom-up cues for Scene Text Recognition
    Anand Mishra, Karteek Alhari and C. V. Jawahar
    CVPR 2012.
    [Paper] [bibtex]
  • An MRF model for Binarization of Natural Scene Text
    Anand Mishra, Karteek Alhari and C. V. Jawahar
    ICDAR 2011. (Oral)
    [Paper] [bibtex]

Teaching

Algorithms and Programming (UE101) -- Monsoon 2018

  • Co-taught at Indian Institute of Science with Dr. Sathish Govindrajan and Dr. Viraj Kumar.
  • Introductory UG course (class strength: 120)

Computer Problem Solving -- Monsoon 2016

  • Taught at IIIT Hyderabad
  • Introductory course for M.Tech. Bioinformatics (class strength: 48)

Computer Architecture (selected topics) -- Spring 2015

  • Co-taught at IIIT Sricity as visiting instructor with Dr. Suresh Purini and Prof. Govindrajulu
  • Introductory UG course (class strength: 60)

Operating Systems -- Monsoon 2014

  • Co-taught at IIIT Sricity as visiting instructor with Dr. Suresh Purini
  • Introductory UG course (class strength: 60)

Computer Vision -- Spring 2014/2011

  • Teaching assistant with Prof. C. V. Jawahar
  • Graduate-level course at IIIT Hyderabad

Stastical Methods in AI -- Monsoon 2013

  • Teaching assistant with Dr. Anoop M.
  • Graduate-level course at IIIT Hyderabad
Web Analytics Made Easy - StatCounter