Mateusz Kozinski

According to our database, Mateusz Kozinski authored at least 27 papers between 2012 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Meta-prompting for Automating Zero-Shot Visual Recognition with LLMs.

Muhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Sivan Doveh, Jakub Micorek, Mateusz Kozinski, Hilde Kuehne, Horst Possegger

Proceedings of the Computer Vision - ECCV 2024, 2024

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection.

Jakub Micorek, Horst Possegger, Dominik Narnhofer, Horst Bischof, Mateusz Kozinski

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Persistent Homology With Improved Locality Information for More Effective Delineation.

Doruk Öner, Adélie Garin, Mateusz Kozinski, Kathryn Hess, Pascal Fua

IEEE Trans. Pattern Anal. Mach. Intell., August, 2023

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections.

Muhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Horst Possegger, Mateusz Kozinski, Rogério Feris, Horst Bischof

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions.

Stefan Leitner, Muhammad Jehanzeb Mirza, Wei Lin, Jakub Micorek, Marc Masana, Mateusz Kozinski, Horst Possegger, Horst Bischof

Proceedings of the IEEE Intelligent Vehicles Symposium, 2023

State-Aware Configuration Detection for Augmented Reality Step-by-Step Tutorials.

Ana Stanescu, Peter Mohr, Mateusz Kozinski, Shohei Mori, Dieter Schmalstieg, Denis Kalkofen

Proceedings of the IEEE International Symposium on Mixed and Augmented Reality, 2023

MATE: Masked Autoencoders are Online 3D Test-Time Learners.

Muhammad Jehanzeb Mirza, Inkyu Shin, Wei Lin, Andreas Schriebl, Kunyang Sun, Jaesung Choe, Mateusz Kozinski, Horst Possegger, In So Kweon, Kuk-Jin Yoon, Horst Bischof

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge.

Wei Lin, Leonid Karlinsky, Nina Shvetsova, Horst Possegger, Mateusz Kozinski, Rameswar Panda, Rogério Feris, Hilde Kuehne, Horst Bischof

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

ActMAD: Activation Matching to Align Distributions for Test-Time-Training.

Muhammad Jehanzeb Mirza, Pol Jané-Soneira, Wei Lin, Mateusz Kozinski, Horst Possegger, Horst Bischof

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Video Test-Time Adaptation for Action Recognition.

Wei Lin, Muhammad Jehanzeb Mirza, Mateusz Kozinski, Horst Possegger, Hilde Kuehne, Horst Bischof

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate.

Doruk Öner, Mateusz Kozinski, Leonardo Citraro, Pascal Fua

IEEE Trans. Medical Imaging, 2022

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation.

Doruk Öner, Mateusz Kozinski, Leonardo Citraro, Nathan C. Dadap, Alexandra Georges Konings, Pascal Fua

IEEE Trans. Pattern Anal. Mach. Intell., 2022

Enforcing Connectivity of 3D Linear Structures Using Their 2D Projections.

Doruk Öner, Hussein Osman, Mateusz Kozinski, Pascal Fua

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2022, 2022

2021

Localized Persistent Homologies for more Effective Deep Learning.

Doruk Öner, Adélie Garin, Mateusz Kozinski, Kathryn Hess, Pascal Fua

CoRR, 2021

2020

Joint Segmentation and Path Classification of Curvilinear Structures.

Agata Mosinska, Mateusz Kozinski, Pascal Fua

IEEE Trans. Pattern Anal. Mach. Intell., 2020

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures.

Mateusz Kozinski, Agata Mosinska, Mathieu Salzmann, Pascal Fua

Medical Image Anal., 2020

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation.

Subeesh Vasu, Mateusz Kozinski, Leonardo Citraro, Pascal Fua

Proceedings of the Computer Vision - ECCV 2020, 2020

Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images.

Leonardo Citraro, Mateusz Kozinski, Pascal Fua

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

Towards Reliable Evaluation of Road Network Reconstructions.

Leonardo Citraro, Mateusz Kozinski, Pascal Fua

CoRR, 2019

2018

Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation.

Mateusz Kozinski, Agata Mosinska, Mathieu Salzmann, Pascal Fua

CoRR, 2018

Learning to Segment 3D Linear Structures Using Only 2D Annotations.

Mateusz Kozinski, Agata Mosinska, Mathieu Salzmann, Pascal Fua

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2018, 2018

Beyond the Pixel-Wise Loss for Topology-Aware Delineation.

Agata Mosinska, Pablo Márquez-Neila, Mateusz Kozinski, Pascal Fua

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017

An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks.

Mateusz Kozinski, Loïc Simon, Frédéric Jurie

CoRR, 2017

2015

A MRF shape prior for facade parsing with occlusions.

Mateusz Kozinski, Raghudeep Gadde, Sergey Zagoruyko, Guillaume Obozinski, Renaud Marlet

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014

Image parsing with graph grammars and Markov Random Fields applied to facade analysis.

Mateusz Kozinski, Renaud Marlet

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

Beyond Procedural Facade Parsing: Bidirectional Alignment via Linear Programming.

Mateusz Kozinski, Guillaume Obozinski, Renaud Marlet

Proceedings of the Computer Vision - ACCV 2014, 2014

2012

High-Level Bottom-Up Cues for Top-Down Parsing of Facade Images.

David Ok, Mateusz Kozinski, Renaud Marlet, Nikos Paragios

Proceedings of the 2012 Second International Conference on 3D Imaging, 2012