6 citations · 7 across the 9 of their papers we have counts for
9 papers
Tables Decoded: DELTA for Structure, TARQA for Understanding
Jahanvi Rajput, Dhruv Kudale, Saikiran Kasturi +2
Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approach…
EMBLEM: Enhancing Multi-script Table Detection through Masking
Dhruv Kudale, Udhay Brahmi, Ganesh Ramakrishnan
Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and visual question answering. While…
DRISHTIKON: Visual Grounding at Multiple Granularities in Documents
Badri Vishal Kasuba, Parag Chaudhuri, Ganesh Ramakrishnan
Visual grounding in text-rich document images is a critical yet underexplored challenge for Document Intelligence and Visual Question Answering (VQA) systems. We present DRISHTIKON…
SPRINT: Script-agnostic Structure Recognition in Tables
Dhruv Kudale, Badri Vishal Kasuba, Venkatapathy Subramanian +2
Table Structure Recognition (TSR) is vital for various downstream tasks like information retrieval, table reconstruction, and document understanding. While most state-of-the-art (S…
PLATTER: A Page-Level Handwritten Text Recognition System for Indic Scripts
Badri Vishal Kasuba, Dhruv Kudale, Venkatapathy Subramanian +2
In recent years, the field of Handwritten Text Recognition (HTR) has seen the emergence of various new models, each claiming to perform competitively better than the other in speci…
StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training
Kaustubh Ponkshe, Venkatapathy Subramanian, Natwar Modani +1
Most state-of-the-art techniques for Language Models (LMs) today rely on transformer-based architectures and their ubiquitous attention mechanism. However, the exponential growth i…
TEXTRON: Weakly Supervised Multilingual Text Detection through Data Programming
Dhruv Kudale, Badri Vishal Kasuba, Venkatapathy Subramanian +2
Several recent deep learning (DL) based techniques perform considerably well on image-based multilingual text detection. However, their performance relies heavily on the availabili…
INSITE: labelling medical images using submodular functions and semi-supervised data programming
Akshat Gautam, Anurag Shandilya, Akshit Srivastava +3
The necessity of large amounts of labeled data to train deep models, especially in medical imaging creates an implementation bottleneck in resource-constrained settings. In Insite…
EIGEN: Expert-Informed Joint Learning Aggregation for High-Fidelity Information Extraction from Document Images
Abhishek Singh, Venkatapathy Subramanian, Ayush Maheshwari +3
Information Extraction (IE) from document images is challenging due to the high variability of layout formats. Deep models such as LayoutLM and BROS have been proposed to address t…