Sanket Biswas
Universidad Autónoma de Barcelona
H-index: 10
Europe-Spain
Top articles of Sanket Biswas
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
arXiv preprint arXiv:2402.11401
2024/2/17
Synthetic dataset of ID and Travel Document
arXiv preprint arXiv:2401.01858
2024/1/3
Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
2024
Beyond document page classification: Design, datasets, and challenges
2024
Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
arXiv preprint arXiv:2310.00558
2023/10/1
TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language
arXiv preprint arXiv:2309.05756
2023/9/11
ICDAR 2023 Competition on Document UnderstanDing of Everything (DUDE)
2023/8/19
Michał Pietruszka
H-Index: 1
Paweł Józiak
H-Index: 3
Sanket Biswas
H-Index: 4
Tomasz Stanisławek
H-Index: 5
SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation
2023/8/19
SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
2023/8/19
Can Pre-trained Language Models Help in Understanding Handwritten Symbols?
2023/8/15
Sanket Biswas
H-Index: 4
Josep Lladós
H-Index: 25
Segmentation-Free Alignment of Arbitrary Symbol Transcripts to Images
2023/8/15
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoder for Text Recognition and Document Enhancement
proceedings of the AAAI conference on artificial intelligence
2023/6/26
The Common Optical Music Recognition Evaluation Framework
arXiv preprint arXiv:2312.12908
2023/12/20
Sanket Biswas
H-Index: 4
SemiDocSeg: Harnessing Semi-Supervised Learning for Document Layout Analysis
2023/11/17
A Few Shot Multi-representation Approach for N-Gram Spotting in Historical Manuscripts
2022/11/25
Doc2Graph: a task agnostic document understanding framework based on graph neural networks
2022/10/23
DocEnTr: An end-to-end document image enhancement transformer
2022/8/21
DocSegTr: an instance-level end-to-end document image segmentation transformer
arXiv preprint arXiv:2201.11438
2022/1/27
Graph-based deep generative modelling for document layout generation
2021/9/2
DocSynth: a layout guided approach for controllable document image synthesis
2021/9/2