Saumik Bhattacharya

I am an Assistant Professor in Department of E&ECE, IIT Kharagpur. My area of research includes statistical learning, computer vision, and image processing.

Email  /  Google Scholar  /  dblp  / 

profile photo
Bio

I am currently an Assistant Professor at IIT Kharagpur. Before joining here, I was a faculty member at IIT Roorkee for a year. I have completed my PhD from IIT Kanpur under the supervision of Prof. Sumana Gupta and Prof. K.S. Venkatesh in 2017 and subsequently joined as a Post-doctoral fellow at the CVPR unit, ISI Kolkata, where I worked till 2018.

Recent Updates

  • [Oct 2023:] One paper has been accepted in WACV 2024. Congrats Alloy, Sanket and Ayan!.
  • [Oct 2023:] Soumyabrata's paper One paper has been accepted in ICVGIP 2023. Congrats Soumyabrata!.
  • [July 2023:] Siladittya Manna's paper has been accepted in IEEE Transactions on Artificial Intelligence. Congrats Siladittya!

    • Conferences
    		SWIS: Self-Supervised Representation Learning for Writer Independent Offline Signature Verification
    Siladittya Manna, Soumitri Chattopadhyay, Saumik Bhattacharya, Umapada Pal,
    IEEE International Conference on Image Processing (ICIP), 2022 (Oral)
    Paper / Slides / arXiv

    We use a decorrelation-based loss to learn decorrelated stroke features from signature images for writer-independent signature verification.

    		SURDS: Self-Supervised Attention-guided Reconstruction and Dual Triplet Loss for Writer Independent Offline Signature Verification
    Soumitri Chattopadhyay, Siladittya Manna, Saumik Bhattacharya, Umapada Pal,
    26th International Conference on Pattern Recognition (ICPR), 2022 (Oral)
    Paper / Video / arXiv

    we use an image reconstruction network using an encoder-decoder architecture that is augmented by a 2D spatial attention mechanism using signature image patches to learn representation. Next, we use a dual-triplet loss based framework for writer independent signature verification tasks.

    Misc
    Basically
    Blog Posts

    Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.