Lei Kang

Computer Vision Center Universitat Autònoma de Barcelona Edifici O, Campus UAB, 08193 Bellaterra, Barcelona, Spain lkang[at]cvc[dot]uab[dot]cat Google Scholar   X   GitHub

Biography

Dr. Lei Kang is a Beatriu de Pinós PostDoc researcher at Computer Vision Center (CVC), Barcelona, Spain, and serves as a Profesor Asociado Laboral at Universitat Autònoma de Barcelona (UAB), Barcelona, Spain.

His research interests are document analysis, document visual question answering, document image generation, medical document analysis, and digital humanities.

Education

• PhD, Computer Vision Center, Universitat Autònoma de Barcelona (UAB), Dec. 2020.

• MSc, Laboratory of Future Networks, University of Science and Technology of China (USTC), July 2015.

• BSc, Automation, Jilin University (JLU), July 2012.

Selected First Author Publications

Journals:

• Preserving Privacy Without Compromising Accuracy: Machine Unlearning for Handwritten Text Recognition
  Lei Kang, Xuanshuo Fu, Lluis Gomez, Alicia Fornés, Ernest Valveny, Dimosthenis Karatzas.
  Pattern Recognition (PR), 2026
  DOI: 10.1016/j.patcog.2025.112411

• Pay Attention To What You Read: Non-recurrent Handwritten Text-line Recognition
  Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas
  Pattern Recognition (PR), 2022
  DOI: 10.1016/j.patcog.2022.108766

• Content and Style Aware Generation of Text-line Images for Handwriting Recognition
  Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
  DOI: 10.1109/TPAMI.2021.3122572

• Candidate Fusion: Integrating Language Modelling Into A Sequence-to-sequence Handwritten Word Recognition Architecture
  Lei Kang, Pau Riba, Mauricio Villegas, Alicia Fornés, Marçal Rusiñol
  Pattern Recognition (PR), 2021
  DOI: 10.1016/j.patcog.2020.107790

Conferences:

• LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis
  Lei Kang, Xuanshuo Fu, Oriol Ramos Terrades, Javier Vazquez-Corral, Ernest Valveny, Dimosthenis Karatzas.
  International Conference on Document Analysis and Recognition (ICDAR), 2025
  DOI: 10.1007/978-3-032-04624-6_36

• GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models
  Lei Kang, Fei Yang, Kai Wang, Mohamed Ali Souibgui, Lluis Gomez, Alicia Fornés, Ernest Valveny, Dimosthenis Karatzas.
  European Conference on Artificial Intelligence (ECAI), 2024
  DOI: 10.3233/FAIA240492

• Machine Unlearning for Document Classification
  Lei Kang, Mohamed Ali Souibgui, Fei Yang, Lluis Gomez, Ernest Valveny, Dimosthenis Karatzas
  International Conference on Document Analysis and Recognition (ICDAR), 2024
  DOI: 10.1007/978-3-031-70546-5_6

• Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism
  Lei Kang, Rubèn Tito, Ernest Valveny, Dimosthenis Karatzas
  International Conference on Document Analysis and Recognition (ICDAR), 2024
  DOI: 10.1007/978-3-031-70552-6_13

• Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup
  Lei Kang, Lichao Zhang, Dazhi Jiang
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023
  DOI: 10.1109/ICASSP49357.2023.10095611

• Distilling Content From Style For Handwritten Word Recognition  (Best Paper Award)
  Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas
  International Conference on Frontiers in Handwriting Recognition (ICFHR), 2020
  DOI: 10.1109/ICFHR2020.2020.00035

• GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
  Lei Kang, Pau Riba, Yaxing Wang, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas
  European Conference on Computer Vision (ECCV), 2020
  DOI: 10.1007/978-3-030-58592-1_17

• Unsupervised Adaptation For Synthetic-to-real Handwritten Word Recognition
  Lei Kang, Marçal Rusiñol, Alicia Fornés, Pau Riba, Mauricio Villegas
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020

• Convolve, Attend and Spell: An Attention-based Sequence-to-sequence Model For Handwritten Word Recognition
  Lei Kang, J.Ignacio Toledo, Pau Riba, Mauricio Villegas, Alicia Fornés, Marçal Rusiñol
  German Conference on Pattern Recognition (GCPR), 2018
  DOI: 10.1007/978-3-030-12939-2 _32

Academic Services

Reviewer for the listed journals and conferences:

• TPAMI, PR, IJCV, IJDAR, MVAP, etc.

• CVPR, ACMMM, ICDAR, BMVC, ICASSP, etc.

Current Teaching

Bachelor courses at Universitat Autònoma de Barcelona (Sep. 2023 to present):

• [MO61134] Vision and Learning. With Lluis Gomez.

• [MO66759] Fundamentals of Natural Language. With Alicia Fornés and Pau Torras.

• [MO80774] Problem Solving. With Pedro Meseguer and Jordi Levy.

Master course at Universitat Autònoma de Barcelona (Mar. 2024 to present):

• [MO82363] Master in Computer Vision (C5 Visual Recognition). With Ernest Valveny and Rubèn Pérez.