Ankan Kumar Bhunia


Undergraduate Student
Jadavpur University, Department of Electrical Engineering
Email: ankankumarbhunia@gmail.com, Mobile: +91-9038858890
Resume Google Scholar GithubLinkedin

My specific area of interest is Deep learning-based visual understanding. I am currently working under the supervision of Dr. Partha Pratim Roy, Assistant Professor, CSE department, Indian Institute of Technology, Roorkee. My research is focused on Deep Learning and its applications in Computer Vision.

 

Recent News

  • NEW 10/2019: 1 paper accepted to Information Fusion
  • NEW 07/2019: 1 paper accepted to Pattern Recognition
  • NEW 03/2019: 1 paper accepted to CVPR 2019
  • NEW 05/2019: 1 paper accepted to ICIP 2019
  • NEW 05/2019: 1 paper accepted to Neural Computing and Application 2019
  • 08/2018: 1 paper accepted to Pattern Recognition 2019
  • 04/2018: 3 papers accepted to ICPR 2018
  •  

    Research Experiences

    University of Manitoba, Winnipeg, Canada
    MITACS Globallink Internship, 2019.
    May 2019 - August 2019 [Certificate] [GitHub]

    Robert Bosch, Bangalore, India
    Computer Vision Lab, RTC Department
    June 2018 - July 2018 [Certificate] [GitHub]

    Indian Institute of Technology Roorkee, India
    Under Prof. Partha Pratim Roy
    June 2017 - Present

     

    Selected Research

    Indic Handwritten Script Identification using Offline-Online Multimodal Deep Network
    Ayan Kumar Bhunia, Subham Mukherjee, Aneeshan Sain, Ankan Kumar Bhunia, Partha Pratim Roy, Umapada Pal
    Information Fusion, 2020. [I.F. 10.716]
    [paper]

    A Deep One-Shot Network for Query-based Logo Retrieval
    Ayan Kumar Bhunia, Ankan Kumar Bhunia, Shuvozit Ghose, Partha Pratim Roy, Umapada Pal
    Pattern Recognition, 2019. [I.F. 5.589]
    [Paper], [arXiv], [GitHub]

    Handwriting Recognition in Low-resource Scripts using Adver-sarial Learning
    Ayan Kumar Bhunia, Abhirup Das, Ankan Kumar Bhunia, Sairaj Kishore, Partha Pratim Roy
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [paper], [GitHub]

    Improving Document Binarization via Adversarial Noise-Texture Augmentation
    Ankan Kumar Bhunia, Ayan Kumar Bhunia, Aneeshan Sain, Partha Pratim Roy
    International Conference on Image Processing (ICIP 2019), IEEE
    [arXiv], [GitHub]

    Script identification in natural scene image and video frames using an attention based Convolutional-LSTM network
    Ankan Kumar Bhunia Aishik Konwar, Abir Bhowmik, Ayan Kumar Bhunia, Partha Pratim Roy
    Pattern Recognition, 2019. [I.F. 3.962]
    [paper], [arXiv], [GitHub]

    Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks
    Ankan Kumar Bhunia, Ayan Kumar Bhunia, Prithaj Banerjee, Aishik Konwer, Abir Bhowmick, Partha Pratim Roy, Umapada Pal
    International Conference on Pattern Recognition (ICPR), 2018
    [paper], [arXiv]

    Signature Verification Approach using Fusion of Hybrid Texture Features
    Ankan Kumar Bhunia, Alireza Alaei, Partha Pratim Roy
    Neural computing and Applications, Springer, 2019. [I.F. 4.231]
    [paper], [arXiv]

    Staff line Removal using Generative Adversarial Networks
    Aishik Konwer, Ayan Kumar Bhunia, Abir Bhowmick, Ankan Kumar Bhunia, Prithaj Banerjee, Partha Pratim Roy, Umapada Pal
    International Conference on Pattern Recognition (ICPR), 2018 (Oral)
    [paper], [arXiv]

    Handwriting Trajectory Recovery using End-to-End Deep Encoder-Decoder Network
    Ayan Kumar Bhunia, Abir Bhowmick, Ankan Kumar Bhunia, Aishik Konwer, Prithaj Banerjee, Partha Pratim Roy, Umapada Pal
    International Conference on Pattern Recognition (ICPR), 2018
    [paper], [arXiv]