Publications

Also on Google Scholar.

2026
Multimodal Large Language Models as Image Classifiers
Nikita Kisel, Illia Volkov, Klara Janouskova, Jiri Matas
CVPR 2026 (Findings Track)
PDF
Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
Matej Suchanek, Klara Janouskova, Ondrej Vasatko, Jiri Matas
arXiv 2025
PDF
2025
Robust Context-Aware Object Recognition
Klara Janouskova, Cristian Gavrus, Jiri Matas
arXiv 2025, under review
PDF
Image Recognition with Vision and Language Embeddings of VLMs
Illia Volkov, Nikita Kisel, Klara Janouskova, Jiri Matas
BMVC 2025
PDF GitHub
SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2
Alen Adamyan, Tomas Cizek, Matej Straka, Klara Janouskova, Martin Schmid
RL4RS @ RLC 2025
PDF
FungiTastic: A Multi-modal Dataset and Benchmark for Image Categorization
Lukas Picek, Klara Janouskova, Vojtech Cermak, Jiri Matas
FGVC @ CVPR 2025
PDF GitHub
Overview of FungiCLEF 2025: Few-Shot Classification with Rare Fungi Species
Klara Janouskova, Jiri Matas, Lukas Picek
Working Notes of CLEF 2025
Overview of LifeCLEF 2025: Challenges on Species Presence Prediction and Identification, and Individual Animal Identification
Lukas Picek, Stefan Kahl, Herve Goeau, Lukas Adam, Theo Larcher, Cesar Leblanc, Maximilien Servajean, Klara Janouskova, Jiri Matas, Vojtech Cermak, et al.
CLEF 2025
LifeCLEF 2025 Teaser: Challenges on Species Presence Prediction and Identification, and Individual Animal Identification
Alexis Joly, Lukas Picek, Stefan Kahl, Herve Goeau, Lukas Adam, Christophe Botella, Maximilien Servajean, Diego Marcos, Cesar Leblanc, Theo Larcher, et al.
ECIR 2025
Flaws of ImageNet, Computer Vision's Favourite Dataset
Nikita Kisel, Illia Volkov, Katerina Hanzelkova, Klara Janouskova, Jiri Matas
ICLR 2025 Blog Posts Track
Blog GitHub
Generating Strong Labels for Examples Labelled with Weak Labels
Klara Janouskova, Ioana Giurgiu, Mattia Rigotti, Cristiano Malossi
US Patent 12,406,478 Patent
2024
Single Image Test-Time Adaptation for Segmentation
Klara Janouskova, Tamir Shor, Chaim Baskin, Jiri Matas
Transactions on Machine Learning Research (TMLR) 2024
PDF GitHub
2023
Towards Workflows for the Use of AI Foundation Models in Visual Inspection Applications
Mattia Rigotti, Diego Antognini, Roy Assaf, Kagan Bakirci, Thomas Frick, Ioana Giurgiu, Klara Janouskova, Filip Janicki, Husam Jubran, Cristiano Malossi, Alexandru Meterez, Florian Scheidegger
EUROSTRUCT 2023
PDF
2022
Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures
Klara Janouskova, Mattia Rigotti, Ioana Giurgiu, Cristiano Malossi
ECCV 2022 Workshop on Computer Vision for Civil and Infrastructure Engineering
★ Best Paper Award
PDF
2021
Text Recognition — Real World Data and Where to Find Them
Klara Janouskova, Jiri Matas, Lluis Gomez, Dimosthenis Karatzas
ICPR 2021
PDF GitHub