Ekta Vats
Biträdande universitetslektor vid Institutionen för informationsteknologi; Systemteknik
- Telefon:
- 018-471 34 40
- E-post:
- ekta.vats@it.uu.se
- Besöksadress:
- Hus 10, Lägerhyddsvägen 1
- Postadress:
- Box 337
751 05 UPPSALA
Ladda ned kontaktuppgifter för Ekta Vats vid Institutionen för informationsteknologi; Systemteknik
Mer information visas för dig som medarbetare om du loggar in.
Kort presentation
Jag är biträdande universitetslektor i maskininlärning samt Beijerforskare vid Beijerlaboratoriet för AI-forskning. Dessutom är jag vetenskaplig ledare för forskningsgruppen Uppsala Vision, Language and Learning där vi bygger grundläggande AI/ML-metoder inom datorseende och språkmodellering för att tackla akuta samhällsutmaningar.
Nyckelord
- artifical intelligence
- computer vision
- data science
- deep learning
- digital humanities
- ethical ai
- handwritten text recognition
- human action recognition
- image analysis
- language modeling
- large language models (llm)
- machine learning
- natural language processing
- ocr
Forskning
Vår forskning är tvärvetenskaplig och kollaborativ, och spänner över ämnen som stora språkmodeller, datorseende, text/bild/videoklassificering, OCR, HTR, mänsklig handlingsanalys och NLP (sentimentanalys, Named Entity Recognition).
Forskningsgrupp: Uppsala Vision, Language and Learning
Publikationer
Urval av publikationer
- Automatic classification of historical texts using a BERT model (2023)
- Paired Image to Image Translation for Strikethrough Removal from Handwritten Words (2022)
- AttentionHTR (2022)
- Word Recognition using Embedded Prototype Subspace Classifiers on a new Imbalanced Dataset (2021)
- Strikethrough Removal from Handwritten Words Using CycleGANs (2021)
- Making large collections of handwritten material easily accessible and searchable (2019)
- Subspace Learning and Classification (2019)
- Embedded Prototype Subspace Classification (2019)
- Creating an Atlas over Handwritten Script Signs (2019)
- In search of the scribe (2019)
- Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion (2019)
- TexT – Text extractor tool for handwritten document transcription and annotation (2018)
- Radial line Fourier descriptor for historical handwritten text representation (2018)
- Radial line Fourier descriptor for historical handwritten text representation (2018)
- An intelligent user interface for efficient semi-automatic transcription of historical handwritten documents (2018)
- Exploring the Applicability of Capsule Networks for WordSpotting in Historical Handwritten Manuscripts (2018)
- Word Spotting in Historical Handwritten Manuscripts using Capsule Networks (2018)
- Learning surrogate models of document image quality metrics for automated document image processing (2018)
- Extracting script features from a large corpus of handwritten documents (2018)
- On-the-fly historical handwritten text annotation (2017)
- Automatic document image binarization using Bayesian optimization (2017)
Senaste publikationer
- Automatic classification of historical texts using a BERT model (2023)
- Paired Image to Image Translation for Strikethrough Removal from Handwritten Words (2022)
- AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks (2022)
- AttentionHTR (2022)
- Word Recognition using Embedded Prototype Subspace Classifiers on a new Imbalanced Dataset (2021)
Alla publikationer
Artiklar
- Word Recognition using Embedded Prototype Subspace Classifiers on a new Imbalanced Dataset (2021)
- The Significance of Script Proportions in the Medieval Swedish Script (2021)
- In search of the scribe (2019)
- Radial line Fourier descriptor for historical handwritten text representation (2018)
Konferenser
- Automatic classification of historical texts using a BERT model (2023)
- Paired Image to Image Translation for Strikethrough Removal from Handwritten Words (2022)
- AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks (2022)
- AttentionHTR (2022)
- Strikethrough Removal from Handwritten Words Using CycleGANs (2021)
- Making large collections of handwritten material easily accessible and searchable (2019)
- Subspace Learning and Classification (2019)
- Embedded Prototype Subspace Classification (2019)
- Creating an Atlas over Handwritten Script Signs (2019)
- Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion (2019)
- TexT – Text extractor tool for handwritten document transcription and annotation (2018)
- Radial line Fourier descriptor for historical handwritten text representation (2018)
- An intelligent user interface for efficient semi-automatic transcription of historical handwritten documents (2018)
- Exploring the Applicability of Capsule Networks for WordSpotting in Historical Handwritten Manuscripts (2018)
- Word Spotting in Historical Handwritten Manuscripts using Capsule Networks (2018)
- Learning surrogate models of document image quality metrics for automated document image processing (2018)
- Extracting script features from a large corpus of handwritten documents (2018)
- On-the-fly historical handwritten text annotation (2017)
- Automatic document image binarization using Bayesian optimization (2017)