Anand Mishra, PhD
CSE-210, Department of Computer Science and Engineering
Indian Institute of Technology Jodhpur
Jodhpur - 342037 (RJ), India

I am an Assistant Professor at the Department of Computer Science and Engineering of the Indian Institute of Technology Jodhpur. Previously, I worked with Dr. Partha Pratim Talukdar and Dr. Anirban Chakraborty at the Indian Institute of Science for nearly two years on Knowledge-aware Computer Vision. I did my PhD working under supervision of Prof. C. V. Jawahar and Dr. Karteek Alahari on understanding text in scene images at IIIT Hyderabad. At IIIT, I was a recipient of Microsoft Research India PhD fellowship 2012 and XRCI best doctoral dissertation award: first runner up 2015.

My current research interest spans Computer Vision, Language and Knowledge Graphs. To be specific, I focus on developing AI models that have the ability to acquire world and commonsense knowledge and use that knowledge to reason about the visual world and address fundamental vision tasks. .

Email | CV | Google Scholar | DBLP | Selected Publications | Teaching | VL2G


Recent/upcoming professional activities:

  • Reviewer and/or PC member for: ICCV 2021, AAAI 2021, IJCAI 2020, ECCV 2020, CVPR 2020, AAAI 2020, ICCV 2019, IJCAI 2019, ICDAR 2019, NCVPRIPG 2019, IEEE TPAMI, IJCV, IEEE TKDD, CVIU, IJDAR, Pattern Recognition.
  • Co-organizer: Workshop on Knwoledge Bases and Multiple Modalities (KBMM) under AKBC 2019/2020.

    • News

    • [July 2021] Our work on Few-shot Visual Relationship Co-Localisation with Revant Teotia, Vaibhav Mishra and Mayank Maheshwari got accepted in ICCV 2021. The paper will be available soon.
    • [June 2021] Got selected for Microsoft Academic Partnership Grant (MAPG) 2021.
    • [April 2021] A paper on TextVQG got accepted in ICDAR 2021. Paper is available here.
    • [February 2021] Presenting a poster on 'Multimodal Machine Learning for Enhanced Image Understanding' under the 'Machine Learning and Big Data Analytics Track', at the 11th Indo German Frontier of Engineering Conference (INDOGFE 2021).
    • [February 2021] Speaking at WADLA 2021 (Virtual event hosted by IIIT Sri City) [Slides].
    • [December 2020] Our ICCV 2019 paper on textKVQA has been accepted for a presentation at Vision India.
    • [August 2020] Received IIT-Jodhpur Teaching Excellence Award 2020 (see announcement).
    • [July 2020] One paper got accepted at ECCV 2020 as spotlight (top-5% paper). This was joint work with Aditay, Rajath and Anirban.
    • [June 2020] Speaking as an invited speaker at Deep Learning for Computer Vision Session at SPCOM 2020 going to be organized virtually at IISc Bangalore.  
    • [June 2020] Got a research grant from the Accenture labs.  
    • [April 2020] Co-organizing 2nd workshop on KBMM co-located with AKBC 2020.  
    • [December 2019] Gave a talk on our recent works on knowledge-aware Computer Vision to a small group of developers/researchers from Siemens at IISc Bangalore.
    • [July 2019] Our paper on "Knowledge-enabled" VQA model that can read got accepted in ICCV 2019 for an oral presentation.
    • [July 2019] Joined IIT-J.
    • Old news
    Selected Publications

    Journals

    • DHFML: deep heterogeneous feature metric learning for matching photograph and cartoon pairs
      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

  • Look, Read and Ask: Learning to Ask Questions by Reading Text in Images ,(NEW)
    Soumya Jahagirdar, Shankar Gangisetty, Anand Mishra,
    ICDAR 2021 (Oral).
    [Paper]

  • Sketch-Guided Object Localization in Natural Images,(NEW)
    Aditay Tripathi, Rajath R. Dani, Anand Mishra, Anirban Chakraborty
    ECCV 2020 (Spotlight Presentation).
    [Paper] [bibtex] [Project page][Code] [Know the paper in 90 seconds] [Know the paper in ten minutes]

  • From Strings to Things: Knowledge-enabled VQA model that can read and reason,(NEW)
    Ajeet Kumar Singh, Anand Mishra, Shashank Shekhar, and Anirban Chakraborty
    ICCV 2019 (oral).
    [Paper] [bibtex] [Project page]

  • OCR-VQA: Visual Question Answering by Reading Text in Images (NEW)
    Anand Mishra, Shashank Shekhar, Ajeet Kumar Singh, and Anirban Chakraborty
    ICDAR 2019.
    [Paper] [bibtex] [Project page]

  • KVQA: Knowledge-aware Visual Question Answering (NEW)
    Sanket Shah*, Anand Mishra*, Naganand Yadati and Partha Pratim Talukdar
    (*: equal contribution) AAAI 2019. (acceptance rate: 16.1%)
    [Paper] [bibtex] [Project page]

  • Deep Embedding using Bayesian Risk Minimization with Application to Sketch Recognition
    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

    (CSL2040) -- Maths for Computing, AY2020-T-3

    • At Indian Institute of Technology Jodhpur.
    • UG course (class strength: 113)
    • Website: https://sites.google.com/iitj.ac.in/m4c/

    (CSL7410) -- Graph Theory and Application, AY2020-T-1

    • At Indian Institute of Technology Jodhpur.
    • Graduate-level course (class strength: 78)

    (CS222) -- Theory of Computations, Spring 2020

    • At Indian Institute of Technology Jodhpur.
    • UG course (class strength: 68)
    • Website: https://sites.google.com/iitj.ac.in/tociit-j/

    (CS212) -- Object-oriented Design and Analysis, Monsoon 2019

    • At Indian Institute of Technology Jodhpur.
    • UG course (class strength: 71)
    • Website: https://sites.google.com/view/ooadiitj/home

    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