32 citations · 111 across the 25 of their papers we have counts for
26 papers
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding
Aniket Pal, Sanket Biswas, Alloy Das +6
Understanding and reasoning over academic handwritten notes remains a challenge in document AI, particularly for mathematical equations, diagrams, and scientific notations. Existin…
Towards Generative Class Prompt Learning for Fine-grained Visual Recognition
Soumitri Chattopadhyay, Sanket Biswas, Emanuele Vivoli +1
Although foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-…
FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
Alloy Das, Sanket Biswas, Umapada Pal +2
The proliferation of scene text in both structured and unstructured environments presents significant challenges in optical character recognition (OCR), necessitating more efficien…
LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach
Maria Pilligua, Nil Biescas, Javier Vazquez-Corral +3
The rapid evolution of intelligent document processing systems demands robust solutions that adapt to diverse domains without extensive retraining. Traditional methods often falter…
DocSynthv2: A Practical Autoregressive Modeling for Document Generation
Sanket Biswas, Rajiv Jain, Vlad I. Morariu +5
While the generation of document layouts has been extensively explored, comprehensive document generation encompassing both layout and content presents a more complex challenge. Th…
DistilDoc: Knowledge Distillation for Visually-Rich Document Applications
Jordy Van Landeghem, Subhajit Maity, Ayan Banerjee +4
This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While V…
GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding
Nil Biescas, Carlos Boned, Josep Lladós +1
This paper presents GeoContrastNet, a language-agnostic framework to structured document understanding (DU) by integrating a contrastive learning objective with graph attention net…
SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition
Adarsh Tiwari, Sanket Biswas, Josep Lladós
We present SketchGPT, a flexible framework that employs a sequence-to-sequence autoregressive model for sketch generation, and completion, and an interpretation case study for sket…
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
Ayan Banerjee, Sanket Biswas, Josep Lladós +1
Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical struc…
A Unified Representation Framework for the Evaluation of Optical Music Recognition Systems
Pau Torras, Sanket Biswas, Alicia Fornés
Modern-day Optical Music Recognition (OMR) is a fairly fragmented field. Most OMR approaches use datasets that are independent and incompatible between each other, making it diffic…
Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
Alloy Das, Sanket Biswas, Ayan Banerjee +3
The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) app…
Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
Alloy Das, Sanket Biswas, Umapada Pal +1
When used in a real-world noisy environment, the capacity to generalize to multiple domains is essential for any autonomous scene text spotting system. However, existing state-of-t…
GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification
Souhail Bakkali, Sanket Biswas, Zuheng Ming +4
Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pr…
High Accuracy Determination of Rheological Properties of Drilling Fluids Using the Marsh Funnel
Sanket Biswas, Harshita Tiwari, Sujata Verma +1
Efficient and safe drilling operations require precise determination of rheological properties in drilling fluids, encompassing dynamic viscosity for Newtonian fluids, and apparent…
Beyond Document Page Classification: Design, Datasets, and Challenges
Jordy Van Landeghem, Sanket Biswas, Matthew B. Blaschko +1
This paper highlights the need to bring document classification benchmarking closer to real-world applications, both in the nature of data tested (: multi-channel, multi-paged,…
SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation
Ayan Banerjee, Sanket Biswas, Josep Lladós +1
Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image. It is a key step in document parsing for their und…
SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Subhajit Maity, Sanket Biswas, Siladittya Manna +4
Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recogni…
A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts
Giuseppe De Gregorio, Sanket Biswas, Mohamed Ali Souibgui +4
Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available…
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
Andrea Gemelli, Sanket Biswas, Enrico Civitelli +2
Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Network…
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
Mohamed Ali Souibgui, Sanket Biswas, Andres Mafla +6
In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text)…
DocEnTr: An End-to-End Document Image Enhancement Transformer
Mohamed Ali Souibgui, Sanket Biswas, Sana Khamekhem Jemni +4
Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for…
DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer
Sanket Biswas, Ayan Banerjee, Josep Lladós +1
Understanding documents with rich layouts is an essential step towards information extraction. Business intelligence processes often require the extraction of useful semantic conte…
Graph-based Deep Generative Modelling for Document Layout Generation
Sanket Biswas, Pau Riba, Josep Lladós +1
One of the major prerequisites for any deep learning approach is the availability of large-scale training data. When dealing with scanned document images in real world scenarios, t…
DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis
Sanket Biswas, Pau Riba, Josep Lladós +1
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task.…