Seuraa
Mateusz Kozinski
Mateusz Kozinski
Vahvistettu sähköpostiosoite verkkotunnuksessa epfl.ch
Nimike
Viittaukset
Viittaukset
Vuosi
Beyond the pixel-wise loss for topology-aware delineation
A Mosinska, P Marquez-Neila, M Koziński, P Fua
Proceedings of the IEEE conference on computer vision and pattern …, 2018
2922018
A convolutional neural network segments yeast microscopy images with high accuracy
N Dietler, M Minder, V Gligorovski, AM Economou, DAHL Joly, A Sadeghi, ...
Nature communications 11 (1), 5723, 2020
1112020
Generating LOD3 building models from structure-from-motion and semantic segmentation
BG Pantoja-Rosero, R Achanta, M Kozinski, P Fua, F Perez-Cruz, K Beyer
Automation in Construction 141, 104430, 2022
542022
A MRF shape prior for facade parsing with occlusions
M Kozinski, R Gadde, S Zagoruyko, G Obozinski, R Marlet
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2015
502015
Match, expand and improve: Unsupervised finetuning for zero-shot action recognition with language knowledge
W Lin, L Karlinsky, N Shvetsova, H Possegger, M Kozinski, R Panda, ...
Proceedings of the IEEE/CVF international conference on computer vision …, 2023
442023
TOPO-Loss for continuity-preserving crack detection using deep learning
BG Pantoja-Rosero, D Oner, M Kozinski, R Achanta, P Fua, F Pérez-Cruz, ...
Construction and Building Materials 344, 128264, 2022
382022
Joint segmentation and path classification of curvilinear structures
A Mosinska, M Koziński, P Fua
IEEE transactions on pattern analysis and machine intelligence 42 (6), 1515-1521, 2019
362019
Drainage canals in Southeast Asian peatlands increase carbon emissions
NC Dadap, AM Hoyt, AR Cobb, D Oner, M Kozinski, PV Fua, K Rao, ...
AGU Advances 2 (1), e2020AV000321, 2021
342021
Lafter: Label-free tuning of zero-shot classifier using language and unlabeled image collections
MJ Mirza, L Karlinsky, W Lin, H Possegger, M Kozinski, R Feris, H Bischof
Advances in Neural Information Processing Systems 36, 5765-5777, 2023
322023
Video test-time adaptation for action recognition
W Lin, MJ Mirza, M Kozinski, H Possegger, H Kuehne, H Bischof
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
312023
Actmad: Activation matching to align distributions for test-time-training
MJ Mirza, PJ Soneira, W Lin, M Kozinski, H Possegger, H Bischof
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
292023
Promoting Connectivity of Network-Like Structures by Enforcing Region Separation
D Oner, M Kozinski, L Citraro, NC Dadap, AG Konings, P Fua
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
282021
Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures
M Koziński, A Mosinska, M Salzmann, P Fua
Medical image analysis 60, 101590, 2020
222020
An adversarial regularisation for semi-supervised training of structured output neural networks
M Koziński, L Simon, F Jurie
arXiv preprint arXiv:1702.02382, 2017
212017
Mate: Masked autoencoders are online 3d test-time learners
MJ Mirza, I Shin, W Lin, A Schriebl, K Sun, J Choe, M Kozinski, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
192023
State-aware configuration detection for augmented reality step-by-step tutorials
A Stanescu, P Mohr, M Kozinski, S Mori, D Schmalstieg, D Kalkofen
2023 IEEE International Symposium on Mixed and Augmented Reality (ISMAR …, 2023
162023
High-level bottom-up cues for top-down parsing of facade images
D Ok, M Kozinski, R Marlet, N Paragios
2012 Second International Conference on 3D Imaging, Modeling, Processing …, 2012
142012
Beyond procedural facade parsing: Bidirectional alignment via linear programming
M Koziński, G Obozinski, R Marlet
Computer Vision--ACCV 2014: 12th Asian Conference on Computer Vision …, 2015
132015
Persistent homology with improved locality information for more effective delineation
D Oner, A Garin, M Koziński, K Hess, P Fua
IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (8), 10588 …, 2023
122023
Meta-prompting for automating zero-shot visual recognition with llms
MJ Mirza, L Karlinsky, W Lin, S Doveh, J Micorek, M Kozinski, H Kuehne, ...
European Conference on Computer Vision, 370-387, 2024
112024
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–20