13133 / 13162 - skupina vizuálního rozpoznávání

Publikační činnost 2025

Články v časopisech WoS

ŠPETLÍK, R., D. FUTSCHIK a D. SÝKORA. StructuReiser: A Structure-preserving Video Stylization Method. COMPUTER GRAPHICS FORUM. 2025, 44(4), ISSN 0167-7055. DOI 10.1111/cgf.70161.

WU, Q. et al. Efficient Minimal Solvers for Relative Pose Estimation With Known Rotation Angle. IEEE Robotics and Automation Letters. 2025, 10(8), 8404-8410. ISSN 2377-3766. DOI 10.1109/LRA.2025.3585382. Dostupné z: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11062722

ADAM, L. et al. Exploiting facial side similarities to improve AI-driven sea turtle photo-identification systems. ECOLOGICAL INFORMATICS. 2025, 89 ISSN 1574-9541. DOI 10.1016/j.ecoinf.2025.103158.

Stati ve sbornících konferencí

KOLÁŘ, J., R. ŠPETLÍK a J. MATAS. EEPPR: Event-based Estimation of Periodic Phenomena Rate using Correlation in 3D. In: Proceedings of SPIE - The International Society for Optical Engineering. 17th International Conference on Machine Vision, ICMV 2024, Edinburg, 2024-10-10/2024-10-13. Bellingham (stát Washington): SPIE, 2025. 1. sv. 13517. ISSN 1996-756X. ISBN 9781510688285. DOI 10.1117/12.3055033.

KORDOPATIS-ZILOS, G. et al. ILIAS: Instance-Level Image retrieval At Scale. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 14777-14787. ISSN 2575-7075. ISBN 979-8-3315-4364-8. DOI 10.1109/CVPR52734.2025.01377. Dostupné z: https://vrg.fel.cvut.cz/ilias/

JAHODA, P. a J. ČECH. Predicting Road Surface Anomalies by Visual Tracking of a Preceding Vehicle. In: IEEE IV2025 36th IEEE Intelligent Vehicles Symposium. IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV 2025), Cluj-Napoca, 2025-06-22/2025-06-25. Piscataway, New Jersey: IEEE Institute of Electrical and Electronics Engineers Inc., 2025. s. 1795-1800. ISSN 2642-7214. ISBN 979-8-3315-3803-3. DOI 10.1109/IV64158.2025.11097610. Dostupné z: https://ieeexplore.ieee.org/document/11097610

OBDRŽÁLEK, Š. a J. MATAS. Auto-calibration of Camera Intrinsics and Extrinsics using Lidar and Motion. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, 2025-10-19/2025-10-25. Beijing: Institute of Electrical and Electronics Engineers, 2025. s. 8741-8748. ISSN 2153-0866. ISBN 979-8-3315-4393-8. DOI 10.1109/IROS60139.2025.11246666. Dostupné z: https://ieeexplore.ieee.org/document/11246666

PSOMAS, V. et al. Instance-Level Composed Image Retrieval. In: Advances in Neural Information Processing Systems 38 (NeurIPS 2025). NeurIPS 2025 The Thirty-Ninth Annual Conference on Neural Information Processing Systems, San Diego, 2025-12-02/2025-12-07. Neural Information Processing Systems Foundation, Inc., 2025. ISSN 1049-5258.

DING, Y. et al. Three-view Focal Length Recovery From Homographies. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 11505-11514. ISSN 1063-6919. ISBN 979-8-3315-4365-5. DOI 10.1109/CVPR52734.2025.01074.

ŠPETLÍK, R. a J. MATAS. Single-Image Localised Reflection Removal with k-Order Differences Term. In: Image Analysis. 23rd Scandinavian Conference, Reykjavik, 2025-06-23/2025-06-25. Springer, Cham, 2025. s. 106-119. 1. sv. 15726 LNCS. ISSN 1611-3349. ISBN 978-3-031-95918-9. DOI 10.1007/978-3-031-95918-9_8. Dostupné z: https://link.springer.com/chapter/10.1007/978-3-031-95918-9_8

ŠKVRNA, J. a L. NEUMANN. MonoSOWA: Scalable Monocular 3D Object Detector Without Human Annotations. In: ICCV2025: Proceedings of the International Conference on Computer Vision. ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 7613-7623. ISSN 1550-5499.

PURKRÁBEK, M. a J. MATAS. Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle. In: ICCV2025: Proceedings of the International Conference on Computer Vision. ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 9004-9013. ISSN 1550-5499.

CHELANI, K. et al. Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Information. In: 2025 International Conference on 3D Vision (3DV). International Conference on 3D Vision 2025, Singapore, 2025-03-25/2025-03-28. IEEE Xplore, 2025. s. 189-199. ISSN 2378-3826. ISBN 979-8-3315-3852-1. DOI 10.1109/3DV66043.2025.00023.

LANGERMAN, J. et al. Explaining Human Preferences via Metrics for Structured 3D Reconstruction. In: ICCV2025: Proceedings of the International Conference on Computer Vision. ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 26944-26953. ISSN 1550-5499.

YPSILANTIS, N. a O. CHUM. Co-segmentation Without any Pixel-Level Supervision with Application to Large-Scale Sketch Classification. In: Computer Vision – ACCV 2024, Part X. ACCV2024: the 17th Asian Conference on Computer Vision, Hanoi, 2024-12-08/2024-12-12. Springer Nature Singapore Pte Ltd., 2025. s. 342-358. LNCS. sv. 15481. ISSN 0302-9743. ISBN 978-981-96-0971-0. DOI 10.1007/978-981-96-0972-7_20.

DING, Y. et al. Fundamental matrix estimation using relative depths. In: Computer Vision – ECCV 2024, Part LXXI. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Springer, Cham, 2025. s. 142-159. LNCS. sv. 15129. ISSN 0302-9743. ISBN 978-3-031-73208-9. DOI 10.1007/978-3-031-73209-6_9.

PURKRÁBEK, M. a J. MATAS. ProbPose: A Probabilistic Approach to 2D Human Pose Estimation. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 27124-27133. ISSN 2575-7075. ISBN 979-8-3315-4364-8. DOI 10.1109/CVPR52734.2025.02526. Dostupné z: https://openaccess.thecvf.com/content/CVPR2025/html/Purkrabek_ProbPose_A_Probabilistic_Approach_to_2D_Human_Pose_Estimation_CVPR_2025_paper.html

VU, T.-H. et al. The BRAVO Semantic Segmentation Challenge Results in UNCV2024. In: Computer Vision – ECCV 2024, Part XVII. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Cham: Springer, 2025. s. 290-306. LNCS. sv. 15639. ISSN 0302-9743. ISBN 978-3-031-91584-0. DOI 10.1007/978-3-031-91585-7_18.

HLAVSA, J. et al. Sex Classification from Human Scent Using Image Interpretation of 2D Gas Chromatography-Mass Spectrometry Data. In: Image Analysis. 23rd Scandinavian Conference, Reykjavik, 2025-06-23/2025-06-25. Springer, Cham, 2025. s. 457-470. 1. sv. 15725 LNCS. ISSN 1611-3349. ISBN 978-3-031-95911-0. DOI 10.1007/978-3-031-95911-0_32. Dostupné z: https://link.springer.com/chapter/10.1007/978-3-031-95911-0_32

JOLY, A. et al. LifeCLEF 2025 Teaser: Challenges on Species Presence Prediction and Identification, and Individual Animal Identification. In: Advances in Information Retrieval. European Conference on Information Retrieval, ECIR 2025, Lucca, 2025-04-06/2025-04-10. Cham: Springer International Publishing, 2025. s. 373-381. LNCS. sv. 15576 LNCS. ISSN 1611-3349. ISBN 978-3-031-88720-8. DOI 10.1007/978-3-031-88720-8_57. Dostupné z: https://link.springer.com/chapter/10.1007/978-3-031-88720-8_57

HADERA, D. et al. BLANKET: Anonymizing Faces in Infant Video Recordings. In: 2025 IEEE International Conference on Development and Learning (ICDL). Praha, 2025-09-16/2025-09-19. Piscataway: IEEE Conference Publications, 2025. ISBN 979-8-3315-4343-3. DOI 10.1109/ICDL63968.2025.11204388. Dostupné z: https://ieeexplore.ieee.org/document/11204388

PICEK, L. et al. FungiTastic: A multi-modal dataset and benchmark for image categorization. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 2037-2047. ISSN 2160-7516. ISBN 979-8-3315-9994-2. DOI 10.1109/CVPRW67362.2025.00192. Dostupné z: https://openaccess.thecvf.com/content/CVPR2025W/FGVC/html/Picek_FungiTastic_A_Multi-Modal_Dataset_and_Benchmark_for_Image_Categorization_CVPRW_2025_paper.html

ŠERÝCH, J., M. NEORAL a J. MATAS. MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, 2025-02-28/2025-03-04. Piscataway: IEEE, 2025. s. 8079-8089. ISSN 2472-6737. ISBN 979-8-3315-1084-8. DOI 10.1109/WACV61041.2025.00784.

BOSÁK, Š., M. ČAPEK a J. MATAS. Q-Factor Evaluation Accelerated by a Deep Neural Network. In: 2025 19th European Conference on Antennas and Propagation (EuCAP). European Conference on Antennas and Propagation, Stockholm, 2025-03-30/2025-04-04. Anchorage, Alaska: IEEE, 2025. ISSN 2164-3342. ISBN 978-88-31299-10-7. DOI 10.23919/EuCAP63536.2025.10999251. Dostupné z: https://ieeexplore.ieee.org/document/10999251

LASKAR, Z. et al. A Dataset for Semantic Segmentation in the Presence of Unknowns. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 1439-1448. ISSN 2575-7075. ISBN 979-8-3315-4364-8. DOI 10.1109/CVPR52734.2025.00142. Dostupné z: https://github.com/vojirt/benchmark_issu

ŠPETLÍK, R., T. UHROVÁ a J. MATAS. Efficient Real-Time Quadcopter Propeller Detection and Attribute Estimation with High-Resolution Event Camera. In: Image Analysis. 23rd Scandinavian Conference, Reykjavik, 2025-06-23/2025-06-25. Springer, Cham, 2025. s. 217-230. 1. sv. 15725 LNCS. ISSN 1611-3349. ISBN 978-3-031-95911-0. DOI 10.1007/978-3-031-95911-0_16. Dostupné z: https://link.springer.com/chapter/10.1007/978-3-031-95911-0_16

TÝBL, O. a L. NEUMANN. Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 14881-14890. ISSN 2575-7075. ISBN 979-8-3315-4364-8. DOI 10.1109/CVPR52734.2025.01386. Dostupné z: https://ieeexplore.ieee.org/document/11093849

ŠKVRNA, J. a L. NEUMANN. TCC-Det: Temporarily Consistent Cues for Weakly-Supervised 3D Detection. In: Computer Vision – ECCV 2024, Part XXVI. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Springer, Cham, 2025. s. 129-145. LNCS. sv. 15084. ISSN 0302-9743. ISBN 978-3-031-73346-8. DOI 10.1007/978-3-031-73347-5_8.

FRANC, V., J. PAPLHÁM a D. PRŮŠA. SCOD: From Heuristics to Theory. In: Computer Vision – ECCV 2024, Part LXXXIV. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Springer, Cham, 2025. s. 424-441. LNCS. sv. 15142. ISSN 0302-9743. ISBN 978-3-031-72906-5. DOI 10.1007/978-3-031-72907-2_25.

LASKAR, Z. et al. Differentiable product quantization for memory efficient camera relocalization. In: LEONARDIS, A. et al., eds. Computer Vision – ECCV 2024 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part LXXXV. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Cham: Springer, 2025. s. 470-489. 1. sv. 15143. ISSN 0302-9743. ISBN 978-3-031-73012-2. DOI 10.1007/978-3-031-73013-9_27.

BARATH, D. et al. StereoGlue: Robust Estimation with Single-Point Solvers. In: Computer Vision – ECCV 2024, Part LVII. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Springer, Cham, 2025. s. 421-441. LNCS. sv. 15115. ISSN 0302-9743. ISBN 978-3-031-72997-3. DOI 10.1007/978-3-031-72998-0_24.

SUCHÁNEK, M., M. PURKRÁBEK a J. MATAS. Human Pose-Constrained UV Map Estimation. In: FRAUNDORFER, F., T. POCK a H. POSSEGGER, eds. Proceedings of the 28th Computer Vision Winter Workshop. 28th Computer Vision Winter Workshop, Graz, 2025-02-12/2025-02-14. Graz: Verlag der Technischen Universität Graz, 2025. s. 27-37. ISBN 978-3-99161-022-9. DOI 10.3217/978-3-99161-022-9-003. Dostupné z: https://diglib.tugraz.at/download.php?id=67ab1fa49578a&location=datacite

EFTHYMIADIS, N. et al. Composed Image Retrieval for Training-Free Domain Conversion. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, 2025-02-28/2025-03-04. Piscataway: IEEE, 2025. s. 1723-1733. ISSN 2472-6737. ISBN 979-8-3315-1084-8. DOI 10.1109/WACV61041.2025.00175.

YPSILANTIS, N. et al. Infusing fine-grained visual knowledge to Vision-Language Models. In: ICCVW2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 4285-4294. ISSN 2473-9936. ISBN 979-8-3315-8989-9. DOI 10.1109/ICCVW69036.2025.00445.

ARAVANIS, T. et al. Only-Style: Stylistic Consistency in Image Generation without Content Leakage. In: ICCVW2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 7000-7010. ISSN 2473-9936. ISBN 979-8-3315-8989-9. DOI 10.1109/ICCVW69036.2025.00723.

TZAMOS, C. et al. Are Minimal Radial Distortion Solvers Necessary for Relative Pose Estimation?. In: ECCV 2024 Workshops - Half-Century of Structure-from-Motion. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Cham: Springer Nature Switzerland AG, 2025. s. 91-107. sv. 15623. ISSN 0302-9743. ISBN 978-3-031-91568-0. DOI 10.1007/978-3-031-91569-7_7.

ŠUMA, P. et al. AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-Level Retrieval. In: Computer Vision – ECCV 2024, Part LIX. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Springer, Cham, 2025. s. 307-325. LNCS. sv. 15117. ISSN 0302-9743. ISBN 978-3-031-73201-0. DOI 10.1007/978-3-031-73202-7_18.

VOJÍŘ, T., J. ŠOCHMAN a J. MATAS. PixOOD: Pixel-Level Out-of-Distribution Detection. In: Computer Vision – ECCV 2024, Part LX. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Cham: Springer, 2025. s. 93-109. LNCS. sv. 15118. ISSN 0302-9743. ISBN 978-3-031-73026-9. DOI 10.1007/978-3-031-73027-6_6.

WU, Q. et al. Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem. In: Computer Vision – ECCV 2024, Part LXV. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Springer, Cham, 2025. s. 160-178. LNCS. sv. 15123. ISSN 0302-9743. ISBN 978-3-031-73649-0. DOI 10.1007/978-3-031-73650-6_10.

KISEL, N. et al. Flaws of ImageNet, Computer Vision's Favorite Dataset. In: International Conference on Learning Representations Blogposts 2025 (ICLR Blogposts 2025). The Thirteenth International Conference on Learning Representations - ICLR 2025, Singapore EXPO, 2025-04-24/2025-04-28. International Conference on Learning Representations, 2025. ISBN 9798331320850.

VOLKOV, I. et al. Image Recognition with Vision and Language Embeddings of VLMs. In: BMVC2025: The 36rd British Machine Vision Conference Proceedings. BMVC2025:The 36th British Machine Vision Conference, Sheffield, 2025-11-24/2025-11-27. Durham: The British Machine Vision Association and Society for Pattern Recognition, 2025. Dostupné z: https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_866/paper.pdf

ČERMÁK, V. et al. WildFusion: Individual Animal Identification with Calibrated Similarity Fusion. In: Computer Vision – ECCV 2024 Workshops, Part II. ECCV2024: The 18th European Conference on Computer Vision, Milano, 2024-09-29/2024-10-04. Cham: Springer, 2025. s. 18-36. LNCS. sv. 15624. ISSN 0302-9743. ISBN 978-3-031-92386-9. DOI 10.1007/978-3-031-92387-6_2.

RAMOS, R. et al. Processing and acquisition traces in visual encoders: What does CLIP know about your camera?. In: ICCV2025: Proceedings of the International Conference on Computer Vision. ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 17056-17066. ISSN 1550-5499.

JANOUŠKOVÁ, K., J. MATAS a L. PICEK. Overview of FungiCLEF 2025: Few-shot classification with rare fungi species. In: Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2025). International Conference of the Cross-Language Evaluation Forum for European Languages (CLEF 2025), Madrid, 2025-09-09/2025-09-12. Aachen: CEUR Workshop Proceedings, 2025. s. 2920-2931. sv. 4038. ISSN 1613-0073.

PICEK, L., V. ČERMÁK a M. HANZL. Zero-shot hazard identification in Autonomous Driving: A Case Study on the COOOL Benchmark. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops. 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, 2025-02-28/2025-03-04. Piscataway: IEEE, 2025. s. 611-620. ISSN 2690-621X. ISBN 979-8-3315-3662-6. DOI 10.1109/WACVW65960.2025.00074. Dostupné z: https://openaccess.thecvf.com/content/WACV2025W/COOOL/html/Picek_Zero-shot_hazard_identification_in_Autonomous_Driving_A_Case_Study_on_WACVW_2025_paper.html

EFTHYMIADIS, N., G. TOLIAS a O. CHUM. Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, 2025-02-28/2025-03-04. Piscataway: IEEE, 2025. s. 1883-1892. ISSN 2472-6737. ISBN 979-8-3315-1084-8. DOI 10.1109/WACV61041.2025.00190.

KRISTAN, M. et al. The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results. In: ICCVW2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 7422-7440. ISSN 2473-9936. ISBN 979-8-3315-8989-9. DOI 10.1109/ICCVW69036.2025.00771.

KHAN, F.F. et al. Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders. In: BMVC2025: The 36rd British Machine Vision Conference Proceedings. BMVC2025:The 36th British Machine Vision Conference, Sheffield, 2025-11-24/2025-11-27. Durham: The British Machine Vision Association and Society for Pattern Recognition, 2025. Dostupné z: https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_701/paper.pdf

TZAMOS, C. et al. Practical Solutions to the Relative Pose of Three Calibrated Cameras. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 21913-21923. ISSN 2575-7075. ISBN 979-8-3315-4364-8. DOI 10.1109/CVPR52734.2025.02041. Dostupné z: https://ieeexplore.ieee.org/document/11093788

STOJNIĆ, V. et al. LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 9794-9803. ISSN 2575-7075. ISBN 979-8-3315-4364-8. DOI 10.1109/CVPR52734.2025.00915. Dostupné z: https://openaccess.thecvf.com/content/CVPR2025/papers/Stojnic_LPOSS_Label_Propagation_Over_Patches_and_Pixels_for_Open-vocabulary_Semantic_CVPR_2025_paper.pdf

WEI, T. et al. Breaking the Frame: Visual Place Recognition by Overlap Prediction. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, 2025-02-28/2025-03-04. Piscataway: IEEE, 2025. s. 2322-2331. ISSN 2472-6737. ISBN 979-8-3315-1084-8. DOI 10.1109/WACV61041.2025.00232.

XIAO, Z. et al. LOCORE: Image Re-ranking with Long-Context Sequence Modeling. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, 2025-06-11/2025-06-15. Los Alamitos: IEEE Computer Society, 2025. s. 9580-9590. ISSN 2575-7075. ISBN 979-8-3315-4364-8. DOI 10.1109/CVPR52734.2025.00895. Dostupné z: https://ieeexplore.ieee.org/document/11093579

DING, Y. et al. RePoseD: Efficient Relative Pose Estimation With Known Depth Information. In: ICCV2025: Proceedings of the International Conference on Computer Vision. ICCV 2025: IEEE International Conference on Computer Vision, Honolulu, 2025-10-19/2025-10-23. Anchorage: IEEE Communications Society, 2025. s. 14876-14886. ISSN 1550-5499.

Výzkumné zprávy

YERMAKOV, A., J. ČECH a J. MATAS. Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detection. [Výzkumná zpráva] ArXiv, 2025. Zpráva č. arXiv:2503.19683.