Ekta Vats
Associate senior lecturer/Assistant Professor at Department of Information Technology; Division of Systems and Control
- Telephone:
- +46 18 471 34 40
- E-mail:
- ekta.vats@it.uu.se
- Visiting address:
- Hus 10, Regementsvägen 10
- Postal address:
- Box 337
751 05 UPPSALA
- Academic merits:
- Docent
- ORCID:
- 0000-0003-4480-3158
Short presentation
I am an Assistant Professor in Machine Learning, Docent in Computerised Image Processing, and a Beijer Researcher at The Beijer Laboratory for Artificial Intelligence Research. I lead the Uppsala Vision, Language and Learning group and our research mission is to build fundamental AI/ML methods for computer vision and language modeling to address societal challenges.
Keywords
- vision-language models (VLMs)
- large language models (LLMs)
- video-LLMs
- machine learning
- deep learning
- computer vision
- image analysis
- handwritten text recognition
- OCR
- natural language processing
- data science
- human action recognition
- artificial intelligence
- multispectral imaging
Research
Our research is highly interdisciplinary and collaborative, and spans topics such as Large Language Models in Computer Vision and NLP, text/image/video classification, text recognition (OCR, Handwritten), multispectral imaging, and NLP tasks (sentiment analysis, Named entity recognition).
Research group: Uppsala Vision, Language and Learning
Media
Beijer Research Group Profile
Get an understanding of my ongoing research in the lab in the video
Beijer Researcher at the Beijer Foundation
How AI and machine learning can help address societal challenges?
https://www.beijerstiftelsen.se/en/component/zoo/researchers/ekta-vats-en?Itemid=234

Publications
Selection of publications
-
Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
2025
-
The Significance of Script Proportions in the Medieval Swedish Charter Script
Part of Arkiv för nordisk filologi, p. 135-162, 2025
-
Part of Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024), p. 111-120, 2024
-
Paired Image to Image Translation for Strikethrough Removal from Handwritten Words
Part of DOCUMENT ANALYSIS SYSTEMS, DAS 2022, p. 309-322, 2022
-
AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks
Part of DOCUMENT ANALYSIS SYSTEMS, DAS 2022, p. 507-522, 2022
-
Strikethrough Removal from Handwritten Words Using CycleGANs
Part of Document Analysis and Recognition -- ICDAR 2021, p. 572-586, 2021
-
Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion
Part of Proc. 15th International Conference on Document Analysis and Recognition, 2019
-
Learning surrogate models of document image quality metrics for automated document image processing
Part of Proc. 13th IAPR International Workshop on Document Analysis Systems, p. 67-72, 2018
-
Automatic document image binarization using Bayesian optimization
Part of Proc. 4th International Workshop on Historical Document Imaging and Processing, p. 89-94, 2017
Recent publications
-
Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
2025
-
The Significance of Script Proportions in the Medieval Swedish Charter Script
Part of Arkiv för nordisk filologi, p. 135-162, 2025
-
Part of Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024), p. 111-120, 2024
-
Automatic classification of historical texts using a BERT model: News about wild berries, 1860-1910
Part of Book of Abstracts, DH Benelux 2023, May 31-June 2, Brussels, Belgium, p. 1-4, 2023
-
Paired Image to Image Translation for Strikethrough Removal from Handwritten Words
Part of DOCUMENT ANALYSIS SYSTEMS, DAS 2022, p. 309-322, 2022
All publications
Articles in journal
-
The Significance of Script Proportions in the Medieval Swedish Charter Script
Part of Arkiv för nordisk filologi, p. 135-162, 2025
-
The Significance of Script Proportions in the Medieval Swedish Script
Part of Arkiv för nordisk filologi, p. 135-162, 2021
-
Word Recognition using Embedded Prototype Subspace Classifiers on a new Imbalanced Dataset
Part of Journal of WSCG, p. 39-47, 2021
-
Part of Human IT, p. 95-120, 2019
-
Radial line Fourier descriptor for historical handwritten text representation
Part of Journal of WSCG, p. 31-40, 2018
Conference papers
-
Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
2025
-
Part of Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024), p. 111-120, 2024
-
Automatic classification of historical texts using a BERT model: News about wild berries, 1860-1910
Part of Book of Abstracts, DH Benelux 2023, May 31-June 2, Brussels, Belgium, p. 1-4, 2023
-
Paired Image to Image Translation for Strikethrough Removal from Handwritten Words
Part of DOCUMENT ANALYSIS SYSTEMS, DAS 2022, p. 309-322, 2022
-
AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks
Part of DOCUMENT ANALYSIS SYSTEMS, DAS 2022, p. 507-522, 2022
-
Strikethrough Removal from Handwritten Words Using CycleGANs
Part of Document Analysis and Recognition -- ICDAR 2021, p. 572-586, 2021
-
Embedded Prototype Subspace Classification: A subspace learning framework
Part of Computer Analysis of Images and Patterns, CAIP 2019, PT II, p. 581-592, 2019
-
Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion
Part of Proc. 15th International Conference on Document Analysis and Recognition, 2019
-
Subspace Learning and Classification
Part of Proc. 3rd Swedish Symposium on Deep Learning, 2019
-
Creating an Atlas over Handwritten Script Signs
Part of Digital Humanities in the Nordic Countries, 2019
-
Making large collections of handwritten material easily accessible and searchable
Part of Digital Libraries, p. 18-28, 2019
-
Extracting script features from a large corpus of handwritten documents
Part of Digital Humanities in the Nordic Countries, 2018
-
Word Spotting in Historical Handwritten Manuscripts using Capsule Networks
2018
-
2018
-
Radial line Fourier descriptor for historical handwritten text representation
Part of Proc. 26th International Conference on Computer Graphics, 2018
-
Learning surrogate models of document image quality metrics for automated document image processing
Part of Proc. 13th IAPR International Workshop on Document Analysis Systems, p. 67-72, 2018
-
Part of Proc. 23rd International Conference on Intelligent User Interfaces Companion, 2018
-
TexT – Text extractor tool for handwritten document transcription and annotation
Part of Digital Libraries and Multimedia Archives, p. 81-92, 2018
-
On-the-fly historical handwritten text annotation
Part of Proc. 14th IAPR International Conference on Document Analysis and Recognition, p. 10-14, 2017
-
Automatic document image binarization using Bayesian optimization
Part of Proc. 4th International Workshop on Historical Document Imaging and Processing, p. 89-94, 2017