Ajeet Kumar Singh
Tata Research Development and Design Center
TCS Innovation Labs, Pune
Pune - 411013 (MH), India

I am a Research Engineer at the Cybersecurity Lab in TCS Research, Pune. I did my MS by Research working under supervision of Prof. C.V. Jawahar and Prof. Anand Mishra (now at IIT Jodhpur) on script and language identification in document images and scene images at IIIT Hyderabad. I also did internship under mentorship of Dr. Nataraj Jammalmadakka (now at Amazon Lab126) at Intel Labs, Bengaluru.

My current research interest spans Computer Vision, Adversarial Machine Learning. To be specific, my aim is to make the deep learning models more robust against the adversarial inputs.

Email: ajeetsingh0712[at]gmail[dot]com / CV  /  Google Scholar /  DBLP

News

  • [Oct 2021] Our papers on privacy prediction and intepretable face verification got accepted at PSTCI@CIKM.
  • [July 2019] Our paper on "Knowledge-enabled" VQA model that can read got accepted in ICCV 2019.
  • [May 2019] Our OCR-VQA paper got accepted in ICDAR 2019.
  • [Mar 2019] Our Phishing URL Classification paper got accepted in CSCML 2019.
  • [Sep 2018] Our Sketch Recognition paper got accepted in ACCV 2018.

Selected Publications
  • Explainable and Personalized Privacy Prediction
    Preetam Prabhu Srikar Dammu, Srinivasa Rao Chalamala, and Ajeet Kumar Singh.
    PSTCI@CIKM 2021
  • Interpretable and Robust Face Verification
    Preetam Prabhu Srikar Dammu, Srinivasa Rao Chalamala, and Ajeet Kumar Singh.
    PSTCI@CIKM 2021
  • A Recommender System for Efficient Implementation of Privacy Preserving Machine Learning Primitives Based on FHE.
    Imtiyazudding Shaik, Ajeet Kumar Singh, Harika Narumanchi, Nitesh Emmadi, Rajan Mindigal Alasingara Bhattachar.
    CSCML 2020
  • From String to Things: Knowledge-enabled VQA Model that can Read and Reason.
    Ajeet Kumar Singh, Anand Mishra, Shashank Shekhar, and Anirban Chakraborty
    ICCV 2019.
    [Paper] [bibtex]
  • OCR-VQA: Visual Question Answering by Reading Text in Images Anand Mishra, Shashank Shekhar, Ajeet Kumar Singh, and Anirban Chakraborty
    ICDAR 2019.
    [Paper] [bibtex][Project page]
  • Everything Is in the Name–A URL Based Approach for Phishing Detection
    Harshal Tupsamudre, Ajeet Kumar Singh, and Sachin Lodha
    CSCML 2019.
    [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]
  • A Simple and Effective method for Script Identification in the Wild
    Ajeet Kumar Singh, Anand Mishra, Pranav Dabral and C. V. Jawahar
    DAS, 2016.
    [Paper] [bibtex]
  • Multilingual OCR for Indic Scripts
    Minesh Mathew, Ajeet Kumar Singh, C.V. Jawahar
    DAS, 2016.
    [Paper] [bibtex]
  • Can RNNs Reliably Separate Script and Language at Word and Line Level?
    Ajeet Kumar Singh, C.V. Jawahar
    ICDAR, 2015.
    [Paper] [bibtex]
  • Towards a Robust OCR System for Indic Scripts
    Praveen Krishnan, Naveen Sankaran, Ajeet Kumar Singh, C.V. Jawahar
    DAS, 2014.
    [Paper] [bibtex]
website counter