no code implementations • 5 Jun 2016 • Pratik Kalshetti, Manas Bundele, Parag Rahangdale, Dinesh Jangra, Chiranjoy Chattopadhyay, Gaurav Harit, Abhay Elhence
They need to be pre-processed before segmentation.
no code implementations • 25 May 2019 • Arka Ujjal Dey, Suman Kumar Ghosh, Ernest Valveny, Gaurav Harit
Images with visual and scene text content are ubiquitous in everyday life.
no code implementations • 27 Feb 2020 • Hiteshi Jain, Gaurav Harit, Avinash Sharma
the reference video and map those variations to the final score.
no code implementations • 22 Aug 2021 • Arka Ujjal Dey, Ernest Valveny, Gaurav Harit
The open-ended question answering task of Text-VQA often requires reading and reasoning about rarely seen or completely unseen scene-text content of an image.
Open-Ended Question Answering Optical Character Recognition (OCR) +1
1 code implementation • 3 Jun 2023 • Sagar Chakraborty, Gaurav Harit, Saptarshi Ghosh
We also propose an end-to-end framework for offline processing of handwritten semi-structured documents, and benchmark it on our novel FIR dataset.