Shamanthak Hegde

Master's in Computer Science, Arizona State University.

prof_pic.png

I am a first year Master’s student at Arizona State University with a passion for Deep Learning and Machine Learning technologies. I am an enthusiast of learning and developing technologies that mimic humans. I have been working on some very interesting Multimodal learning: Vision and Language tasks which include Scene text understanding and Visual Question Answering.

In my undergraduate, I worked with Prof. Shankar Gangisetty on various projects in the VQA domain.

My Research Interests are: Machine Learning | Deep Learning | Computer Vision | Natural Language Processing | Multi-modal Learning: Vision and Language

News

Aug, 2023 Joined Arizona State University to pursue Master’s in Computer Science (MSCS)!
Jun, 2023 Completed Bachelor of Engineering(BE) in Computer Science from KLE Tech! (CGPA: 8.18/10)
Apr, 2023 2 papers accepted to CVPR workshop (O-DRUM)!
1] Making the V in Text-VQA Matter 2] Weakly Supervised Visual Question Answer Generation
May, 2021 Joined Multi-modal Learning Lab and started working on multi-modal learning, specifically focusing on vision and language modalities. Advisor: Prof. Shankar Gangisetty

Recent Papers

  1. mtvtvqam.png
    Making the V in Text-VQA Matter
    Shamanthak HegdeSoumya Jahagirdar, and Shankar Gangisetty
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2023
  2. wsvqag.png
    Weakly Supervised Visual Question Answer Generation
    Charani Alampalle, Shamanthak HegdeSoumya Jahagirdar, and Shankar Gangisetty
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2023