Soumya Shamarao Jahagirdar
I am a Master's by Research student at CVIT, IIIT Hyderabad, India. I work under the guidance of Prof. C V Jawahar and Prof. Dimosthenis Karatzas from Computer Vision Center (CVC), UAB, Spain. My master's research is centered around multimodal learning. More specifically I am working on Vision and Language tasks like Image and Video Question Answering.
Previously I have worked with Prof. Shankar Gangisetty on text-based multimodal learning. I have also worked as a Research Assistant with Prof. B A Patil at Think & Ink Education and Research Foundation, on magnitude spectrum and descriptive statistics on color models for soil classification.
I was a part of mentors at Winter Workshop and an active member at Computer Vision and Graphics Lab, KLE Technological University, Hubballi, India.
I completed my B.E. in Computer Science and Engineering from KLE Technological University in 2021.
More about me!
I make friends very easily. I love sketching, it takes me to a transe-phase. Animals have my heart and I look forward to groom them throughout my life. I occasionally sing (I have learnt Hidustani Music for over 10 years) and yeah, I can cook some great dishes. Walking, badminton, running, home workout sessions help me balance the amount of food I consume on daily basis. To know more you know where to ping me!
Email  / 
CV  / 
Google Scholar  / 
LinkedIn / 
Github  / 
Twitter / 
More Me!
|
|
News!
- October 2022: Our paper "Watching the News: Towards VideoQA Models that can Read" got accepted in WACV, 2023.
- September 2022: I started my internship at Computer Vision Center (CVC), UAB, Barcelona, Spain.
- July 2022: Conducted a tutorial on transformers in Summer School of AI, CVIT, IIIT-Hyderabad, 2022.
- July 2022: Participated in student orgainising team in Summer School of AI, CVIT, IIIT-Hyderabad, 2022.
- May 2022: First Patent on Single Image Depth Estimation with SRIB-Bangalore got accpeted.
Research
My research interests lie in Computer Vision, Deep Learning, Machine Learning, Multimodal Learning and Natural Language Processing. This field of study excites me and pushes me to work much harder everyday.
|
Publications
Watching the News: Towards VideoQA Models that can Read, WACV, 2023.
Soumya Shamarao Jahagirdar, Minesh Mathew, Dimosthenis Karatzas, C. V. Jawahar
More details coming soon!
Look, Read and Ask: Learning to Ask Questions by Reading Text in Images
Soumya Shamarao Jahagirdar, Shankar Gangisetty, Anand Mishra.
project page /
video /
code
DeepDNet: Deep Dense Network for Depth Completion Task
Girish Hegde, Tushar Pharale, Soumya Jahagirdar, Vaishakh Nargund, Ramesh Ashok Tabib, Uma Mudenagudi, Basavaraja Vandrotti, Ankit Dhiman
WiCV, CVPR, 2021.
The website has been designed based on https://jonbarron.info/. I thank him for the wonderful source code he provided.
|