Search Results for author: Soumya Jahagirdar

Found 5 papers, 0 papers with code

Understanding Video Scenes through Text: Insights from Text-based Video Question Answering

no code implementations4 Sep 2023 Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas, C. V. Jawahar

Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes effectively.

Domain Adaptation Question Answering +1

Making the V in Text-VQA Matter

no code implementations1 Aug 2023 Shamanthak Hegde, Soumya Jahagirdar, Shankar Gangisetty

Such a simple, yet effective approach increases the understanding and correlation between the image features and text present in the image, which helps in the better answering of questions.

Optical Character Recognition (OCR) Visual Question Answering (VQA)

Weakly Supervised Visual Question Answer Generation

no code implementations11 Jun 2023 Charani Alampalle, Shamanthak Hegde, Soumya Jahagirdar, Shankar Gangisetty

To address this issue, we propose a weakly-supervised visual question answer generation method that generates a relevant question-answer pairs for a given input image and associated caption.

Answer Generation Dependency Parsing +4

Look, Read and Ask: Learning to Ask Questions by Reading Text in Images

no code implementations23 Nov 2022 Soumya Jahagirdar, Shankar Gangisetty, Anand Mishra

However, it is challenging as it requires an in-depth understanding of the scene and the ability to semantically bridge the visual content with the text present in the image.

Optical Character Recognition (OCR) Question Answering +4

Watching the News: Towards VideoQA Models that can Read

no code implementations10 Nov 2022 Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas, C. V. Jawahar

We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.

Question Answering Video Question Answering +1

Cannot find the paper you are looking for? You can Submit a new open access paper.