@inproceedings{ilias2025,
  title={{ILIAS}: Instance-Level Image retrieval At Scale},
  author={Kordopatis-Zilos, Giorgos and Stojnić, Vladan and Manko, Anna and Šuma, Pavel and Ypsilantis, Nikolaos-Antonios and Efthymiadis, Nikos and Laskar, Zakaria and Matas, Jiří and Chum, Ondřej and Tolias, Giorgos},
  booktitle={Computer Vision and Pattern Recognition (CVPR)},
  year={2025},
}

@inproceedings{stojnic2025lposs,
	author = {Vladan Stojnić and
                  Yannis Kalantidis and
                  Jiří Matas and
                  Giorgos Tolias},
	title = {LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation},
	booktitle = {{CVPR}},
	year = {2025}
}

@inproceedings{laskar_cvpr2025,
    title={{A Dataset for Semantic Segmentation in the Presence of Unknowns}},
    author={Zakaria Laskar and Tomáš Vojíř and Matej Grcic and Iaroslav Melekhov and Shankar Gangisetty and Juho~Kannala and Jiri Matas and Giorgos Tolias and C.V. Jawahar},
    booktitle={CVPR},
    year={2025},
}

@inproceedings{probpose2025,
  title={ProbPose: A Probabilistic Approach to 2D Human Pose Estimation},
  author={Miroslav Purkrabek and Jiri Matas},
  booktitle={Computer Vision and Pattern Recognition (CVPR)},
  year={2025},
}

@inproceedings{crafting2025,
  title={Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization},
  author={Efthymiadis, Nikos and Tolias, Giorgos and Chum, Ondřej},
  booktitle={IEEE Winter Conference on Applications of Computer Vision},
  year={2025}
}

@inproceedings{composed2025,
  title={Composed Image Retrieval for Training-Free Domain Conversion},
  author={Efthymiadis, Nikos and Psomas, Bill and Laskar, Zakaria and Karantzalos, Konstantinos and Avrithis, Yannis and Chum, Ondřej and Tolias, Giorgos},
  booktitle={IEEE Winter Conference on Applications of Computer Vision},
  year={2025}
}

@inproceedings{serych2025mftiq,
	       title={{MFTIQ}: Multi-Flow Tracker with Independent Matching Quality Estimation},
	       author={Serych, Jonas and Neoral, Michal and Matas, Jiri},
	       journal={arXiv preprint arXiv:2411.09551},
	       year={2024},
}

@article{wei2024breaking,
  title={Breaking the Frame: Visual Place Recognition by Overlap Prediction},
  author={Wei, Tong and Lindenberger, Philipp and Matas, Jiri and Barath, Daniel},
  journal={arXiv preprint arXiv:2406.16204},
  year={2024}
}

@InProceedings{10.1007/978-981-96-0972-7_20,
author="Ypsilantis, Nikolaos-Antonios
and Chum, Ond{\v{r}}ej",
editor="Cho, Minsu
and Laptev, Ivan
and Tran, Du
and Yao, Angela
and Zha, Hongbin",
title="Co-segmentation Without any Pixel-Level Supervision with Application to Large-Scale Sketch Classification",
booktitle="Computer Vision -- ACCV 2024",
year="2025",
publisher="Springer Nature Singapore",
address="Singapore",
pages="342--358",
abstract="This work proposes a novel method for object co-segmentation, i.e. pixel-level localization of a common object in a set of images, that uses no pixel-level supervision for training. Two pre-trained Vision Transformer (ViT) models are exploited: ImageNet classification-trained ViT, whose features are used to estimate rough object localization through intra-class token relevance, and a self-supervised DINO-ViT for intra-image token relevance. On recent challenging benchmarks, the method achieves state-of-the-art performance among methods trained with the same level of supervision (image labels) while being competitive with methods trained with pixel-level supervision (binary masks).",
isbn="978-981-96-0972-7"
}

@inproceedings{pizzi2024vsc,
  title = {The 2023 video similarity dataset and challenge},
  author = {Pizzi, Ed and Kordopatis-Zilos, Giorgos and Patel, Hiral and Postelnicu, Gheorghe and Ravindra, Sugosh Nagavara and Gupta, Akshay and Papadopoulos, Symeon and Tolias, Giorgos and Douze, Matthijs},
  booktitle = {Computer Vision and Image Understanding (CVIU)},
  year = {2024},
}

@inproceedings{stojnic2024label,
	author = {Vladan Stojnić and
                  Yannis Kalantidis and
                  Giorgos Tolias},
	title = {Label Propagation for Zero-shot Classification with Vision-Language
                  Models},
	booktitle = {{CVPR}},
	year = {2024}
}

@inproceedings{10.1007/978-3-031-72998-0_24,
	author = {Barath, Daniel
and Mishkin, Dmytro
and Cavalli, Luca
and Sarlin, Paul-Edouard
and Hruby, Petr
and Pollefeys, Marc},
	editor = {Leonardis, Ale{\v{s}}
and Ricci, Elisa
and Roth, Stefan
and Russakovsky, Olga
and Sattler, Torsten
and Varol, G{\"u}l},
	title = {StereoGlue: Robust Estimation with Single-Point Solvers},
	booktitle = {Computer Vision -- ECCV 2024},
	year = {2025},
	publisher = {Springer Nature Switzerland},
	address = {Cham},
	pages = {421--441},
	abstract = {We propose StereoGlue, a method designed for joint feature matching and robust estimation that effectively reduces the combinatorial complexity of these tasks using single-point minimal solvers. StereoGlue is applicable to a range of problems, including but not limited to relative pose and homography estimation, determining absolute pose with 2D-3D correspondences, and estimating 3D rigid transformations between point clouds. StereoGlue starts with a set of one-to-many tentative correspondences, iteratively forms tentative matches, and estimates the minimal sample model. This model then facilitates guided matching, leading to consistent one-to-one matches, whose number serves as the model score. StereoGlue is superior to the state-of-the-art robust estimators on real-world datasets on multiple problems, improving upon a number of recent feature detectors and matchers. Additionally, it shows improvements in point cloud matching and absolute camera pose estimation. The code is at: https://github.com/danini/stereoglue.},
	isbn = {978-3-031-72998-0}
}

@article{Nguyen-Ha24:371779,
	author = {Nguyen-Ha, P. and Huynh, L. and Rahtu, E., and Matas, J.},
	title = {Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis},
	year = {2024},
	journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
	language = {English},
	url = {https://ieeexplore.ieee.org/abstract/document/10328666},
	doi = {10.1109/TPAMI.2023.3335311}
}

@article{Wang24:372774,
	author = {Wang, S. and Laskar, Z. and Melekhov, I. and Li, X. and Zhao, Y. and Tolias, G., and Kannala, J.},
	title = {HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer},
	year = {2024},
	journal = {International Journal of Computer Vision},
	language = {English},
	url = {https://link.springer.com/article/10.1007/s11263-023-01982-9},
	doi = {10.1007/s11263-023-01982-9}
}

@inproceedings{NEURIPS2024_9df6a759,
 author = {Ypsilantis, Nikolaos-Antonios and Chen, Kaifeng and Araujo, Andre and Chum, Ondrej},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},
 pages = {86836--86859},
 publisher = {Curran Associates, Inc.},
 title = {UDON: Universal Dynamic Online distillatioN for generic image representations},
 url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/9df6a759e01b871a009138bcc0471607-Paper-Conference.pdf},
 volume = {37},
 year = {2024}
}

@article{
janouskova2024single,
title={Single Image Test-Time Adaptation for Segmentation},
author={Klara Janouskova and Tamir Shor and Chaim Baskin and Jiri Matas},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2024},
url={https://openreview.net/forum?id=68LsWm2GuD},
note={}
}

@inproceedings{Neoral24:373794,
	author = {Neoral, M. and {\v S}er{\' y}ch, J., and Matas, J.},
	title = {{MFT}: Long-Term Tracking of Every Pixel},
	booktitle = {2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2024},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10484299},
	doi = {10.1109/WACV57701.2024.00669}
}

@inproceedings{stojnic2024training,
	author = {Vladan Stojnić and
                  Zakaria Laskar and
                  Giorgos Tolias},
	title = {Training Ensembles with Inliers and Outliers for Semi-supervised Active
                  Learning},
	booktitle = {{WACV}},
	pages = {259--268},
	publisher = {{IEEE}},
	year = {2024}
}

@inproceedings{Vavra2023,
	author = {Vávra, Václav and Mishkin, Dmytro and Matas, Jiří},
	booktitle = {2023 IEEE International Conference on Image Processing (ICIP)},
	title = {DoG Accuracy Via Equivariance: Get The Interpolation Right},
	year = {2023},
	volume = {},
	number = {},
	pages = {136-140},
	keywords = {Interpolation;Image matching;Focusing;Detectors;Dogs;Feature extraction;Libraries;Difference of Gaussians;feature detector;local features;OpenCV;Kornia},
	doi = {10.1109/ICIP49359.2023.10222153}
}

@inproceedings{Subrtova23:367657,
	author = {{\v S}ubrtov{\' a}, A. and Luk{\' a}{\v c}, M. and {\v C}ech, J. and Futschik, D. and Shechtman, E., and S{\' y}kora, D.},
	title = {Diffusion Image Analogies},
	booktitle = {ACM SIGGRAPH 2023 Conference Proceedings},
	publisher = {ACM SIGGRAPH},
	address = {New York, US},
	year = {2023},
	language = {English},
	url = {https://dcgi.fel.cvut.cz/home/sykorad/dia.html},
	doi = {10.1145/3588432.3591558}
}

@inproceedings{Barath23:367030,
	author = {Barath, D. and Mishkin, D. and Polic, M. and Forstner, W., and Matas, J.},
	title = {A Large-Scale Homography Benchmark},
	booktitle = {Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	publisher = {IEEE Computer Society},
	address = {USA, US},
	year = {2023},
	language = {English},
	url = {https://openaccess.thecvf.com/content/CVPR2023/papers/Barath_A_Large-Scale_Homography_Benchmark_CVPR_2023_paper.pdf},
	doi = {10.1109/CVPR52729.2023.02046}
}

@inproceedings{Chelani23:371977,
	author = {Chelani, K. and Sattler, T. and Kahl, F., and K{\' u}kelov{\' a}, Z.},
	title = {Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses},
	booktitle = {Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	publisher = {IEEE Computer Society},
	address = {USA, US},
	year = {2023},
	language = {English},
	url = {https://openaccess.thecvf.com/content/CVPR2023/papers/Chelani_Privacy-Preserving_Representations_Are_Not_Enough_Recovering_Scene_Content_From_Camera_CVPR_2023_paper.pdf},
	doi = {10.1109/CVPR52729.2023.01262}
}

@inproceedings{Panek23:367543,
	author = {P{\' a}nek, V. and K{\' u}kelov{\' a}, Z., and Sattler, T.},
	title = {Visual Localization using Imperfect 3D Models from the Internet},
	booktitle = {Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	publisher = {IEEE Computer Society},
	address = {USA, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10204034},
	doi = {10.1109/CVPR52729.2023.01266}
}

@inproceedings{Barath23:371780,
	author = {Barath, D. and Rozumnyi, D. and Eichhardt, I. and Hajder, L., and Matas, J.},
	title = {Finding Geometric Models by Clustering in the Consensus Space},
	booktitle = {Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	publisher = {IEEE Computer Society},
	address = {USA, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10203844},
	doi = {10.1109/CVPR52729.2023.00524}
}

@inproceedings{Wei23:370527,
	author = {Wei, T. and Patel, Y. and Shekhovtsov, O. and Matas, J., and Bar{\' a}th, D.},
	title = {Generalized Differentiable RANSAC},
	booktitle = {ICCV2023: Proceedings of the International Conference on Computer Vision},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10378404},
	doi = {10.1109/ICCV51070.2023.01618}
}

@inproceedings{Wei23:369997,
	author = {Wei, T. and Matas, J., and Bar{\' a}th, D.},
	title = {Adaptive Reordering Sampler with Neurally Guided MAGSAC},
	booktitle = {ICCV2023: Proceedings of the International Conference on Computer Vision},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10378195},
	doi = {10.1109/ICCV51070.2023.01665}
}

@inproceedings{Mohwald23:370501,
	author = {M{\" o}hwald, A. and Jen{\' i}{\v c}ek, T., and Chum, O.},
	title = {Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning},
	booktitle = {ICCV2023: Proceedings of the International Conference on Computer Vision},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://openaccess.thecvf.com/content/ICCV2023/papers/Mohwald_Dark_Side_Augmentation_Generating_Diverse_Night_Examples_for_Metric_Learning_ICCV_2023_paper.pdf},
	doi = {10.1109/ICCV51070.2023.01024}
}

@inproceedings{Ypsilantis23:370772,
	author = {Ypsilantis, N. and Chen, K. and Cao, B. and Lipovsk{\' y}, M. and Dogan-Sch{\" o}nberger, P. and Makosa, G. and Bluntschli, B. and Seyedhosseini, M. and Chum, O., and Araujo, A.},
	title = {Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations},
	booktitle = {ICCV2023: Proceedings of the International Conference on Computer Vision},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10378138},
	doi = {10.1109/ICCV51070.2023.01037}
}

@inproceedings{Rozumnyi23:371803,
	author = {Rozumnyi, D. and Matas, J. and Pollefeys, M. and Ferrari, V., and Oswald, M.R.},
	title = {Tracking by 3D Model Estimation of Unknown Objects in Videos},
	booktitle = {ICCV2023: Proceedings of the International Conference on Computer Vision},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10378060},
	doi = {10.1109/ICCV51070.2023.01295}
}

@inproceedings{Ventura23:372033,
	author = {Ventura, J. and K{\' u}kelov{\' a}, Z. and Sattler, T., and Bar{\' a}th, D.},
	title = {P1AC: Revisiting Absolute Pose From a Single Affine Correspondence},
	booktitle = {ICCV2023: Proceedings of the International Conference on Computer Vision},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	doi = {10.1109/ICCV51070.2023.01809}
}

@inproceedings{vojir2023calibrated,
  author = {Voj{\'\i}\v{r}, Tom\'a\v{s} and \v{S}ochman, Jan and Aljundi, Rahaf and Matas, Ji\v{r}{\'\i}},
  title = {Calibrated Out-of-Distribution Detection with a Generic Representation},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
  month = oct,
  year = {2023},
  pages = {4507-4516},
}

@inproceedings{Simsa23:371807,
	author = {{\v S}imsa, {\v S}. and {\v S}ulc, M. and U{\v r}i{\v c}{\' a}{\v r}, M. and Patel, Y., and Matas, J.},
	title = {DocILE Benchmark for Document Information Localization and Extraction},
	booktitle = {ICDAR 2023: Proceedings of the Document Analysis and Recognition, Part II},
	publisher = {Springer},
	address = {Cham, CH},
	year = {2023},
	series = {LNCS},
	volume = {14188},
	language = {English},
	url = {https://link.springer.com/chapter/10.1007/978-3-031-41679-8_9},
	doi = {10.1007/978-3-031-41679-8_9}
}

@inproceedings{Shekhovtsov23:371050,
	author = {Shekhovtsov, O.},
	title = {Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator},
	booktitle = {International Conference on Machine Learning (ICML)},
	publisher = {Proceedings of Machine Learning Research},
	address = {Honolulu, USA},
	year = {2023},
	language = {English},
	url = {https://proceedings.mlr.press/v202/shekhovtsov23a.html}
}

@article{Javed23:366877,
	author = {Javed, S. and Danelljan, M. and Khan, F. and Khan, M., and Matas, J.},
	title = {Visual Object Tracking With Discriminative Filters and Siamese Networks: A Survey and Outlook},
	year = {2023},
	number = {5},
	journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
	volume = {45},
	language = {English},
	url = {https://arxiv.org/pdf/2112.02838.pdf},
	doi = {10.1109/TPAMI.2022.3212594}
}

@article{Dai23:364658,
	author = {Dai, D. and Vasudevan, A. and Matas, J., and Van Gool, L.},
	title = {Binaural SoundNet: Predicting Semantics, Depth and Motion With Binaural Sounds},
	year = {2023},
	number = {1},
	journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
	volume = {45},
	month = {January},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/9726801},
	doi = {10.1109/TPAMI.2022.3155643}
}

@inproceedings{Rustler23:370922,
	author = {Rustler, L. and Matas, J., and Hoffmann, M.},
	title = {Efficient Visuo-Haptic Object Shape Completion for Robot Manipulation},
	booktitle = {2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10342200},
	doi = {10.1109/IROS55552.2023.10342200}
}

@inproceedings{Bertrand23:370562,
	author = {Bertrand, J. and Kordopatis-Zilos, G. and Kalantidis, Y., and Tolias, G.},
	title = {Test-time Training for Matching-based Video Object Segmentation},
	booktitle = {Advances in Neural Information Processing Systems 36 (NeurIPS 2023)},
	publisher = {Neural Information Processing Society},
	address = {Montreal, CA},
	year = {2023},
	language = {English},
	url = {https://openreview.net/pdf?id=9QsdPQlWiE}
}

@inproceedings{Vojir23:362931,
	author = {Voj{\' i}{\v r}, T. and Matas, J.},
	title = {Image-Consistent Detection of Road Anomalies As Unpredictable Patches},
	booktitle = {Proc. of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://openaccess.thecvf.com/content/WACV2023/html/Vojir_Image-Consistent_Detection_of_Road_Anomalies_As_Unpredictable_Patches_WACV_2023_paper.html},
	doi = {10.1109/WACV56688.2023.00545}
}

@inproceedings{Serych23:371649,
	author = {{\v S}er{\' y}ch, J. and Matas, J.},
	title = {Planar Object Tracking via Weighted Optical Flow},
	booktitle = {Proc. of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10030801},
	doi = {10.1109/WACV56688.2023.00164}
}

@inproceedings{Suma23:362078,
	author = {{\v S}uma, P. and Tolias, G.},
	title = {Large-to-small Image Resolution Asymmetry in Deep Metric Learning},
	booktitle = {Proc. of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/10030552},
	doi = {10.1109/WACV56688.2023.00150}
}

@inproceedings{Bhayani23:371941,
	author = {Bhayani, S. and Sattler, T. and Larsson, V. and Heikkila, J., and K{\' u}kelov{\' a}, Z.},
	title = {Partially calibrated semi-generalized pose from hybrid point correspondences},
	booktitle = {Proc. of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2023},
	language = {English},
	doi = {10.1109/WACV56688.2023.00290}
}

@inproceedings{Barath22:361443,
	author = {Bar{\' a}th, D. and Noskov{\' a}, J. and Eichhardt, I., and Matas, J.},
	title = {Pose-graph via Adaptive Image Re-ordering},
	booktitle = {The 33rd British Machine Vision Conference Proceedings},
	publisher = {The British Machine Vision Association and Society for Pattern Recognition},
	address = {Durham, GB},
	year = {2022},
	language = {English},
	url = {https://bmvc2022.mpi-inf.mpg.de/0127.pdf}
}

@inproceedings{Trojer22:363005,
	author = {Trojer, Z. and Lukezic, A. and Matas, J., and Kristan, M.},
	title = {Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking},
	booktitle = {The 33rd British Machine Vision Conference Proceedings},
	publisher = {The British Machine Vision Association and Society for Pattern Recognition},
	address = {Durham, GB},
	year = {2022},
	language = {English},
	url = {https://bmvc2022.mpi-inf.mpg.de/470/}
}

@inproceedings{Martyniuk22:362947,
	author = {Martyniuk, T. and Kupyn, O. and Kurlyak, Y. and Krashenyi, I. and Matas, J., and Sharmanska, V.},
	title = {DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image},
	booktitle = {Proceeding 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2022},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/9878647},
	doi = {10.1109/CVPR52688.2022.02027}
}

@inproceedings{Ding22:362925,
	author = {Ding, Y. and Bar{\' a}th, D. and Yang, J., and K{\' u}kelov{\' a}, Z.},
	title = {Relative Pose from a Calibrated and an Uncalibrated Smartphone Image},
	booktitle = {Proceeding 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	publisher = {IEEE},
	address = {Piscataway, US},
	year = {2022},
	language = {English},
	url = {https://ieeexplore.ieee.org/document/9880282},
	doi = {10.1109/CVPR52688.2022.01243}
}