13133 / 13162 - Visual Recognition Group

Publications 2021

Papers in WoS Journals

LUKEZIC, A., et al. Performance Evaluation Methodology for Long-Term Single-Object Tracking. IEEE Transactions on Cybernetics. 2021, 51(12), 6305-6318. ISSN 2168-2267. DOI 10.1109/TCYB.2020.2980618.

PRITTS, J., et al. Minimal Solvers for Rectifying from Radially-Distorted Conjugate Translations. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021, 43(11), 3931-3948. ISSN 1939-3539. DOI 10.1109/TPAMI.2020.2992261. Available from: https://ieeexplore.ieee.org/document/9086062

ROZUMNYI, D., et al. Tracking by Deblatting. International Journal of Computer Vision. 2021, 2021(129), 2583-2604. ISSN 0920-5691. DOI 10.1007/s11263-021-01480-w.

JIN, Y., et al. Image Matching across Wide Baselines: From Paper to Practice. International Journal of Computer Vision. 2021, 129 517-547. ISSN 0920-5691. DOI 10.1007/s11263-020-01385-0.

DJUKANOVIC, S., J. MATAS, and T. VIRTANEN. Acoustic vehicle speed estimation from single sensor measurements. IEEE Sensors Journal. 2021, 21(20), 23317-23324. ISSN 1530-437X. DOI 10.1109/JSEN.2021.3110009.

Patents

České vysoké učení technické v Praze, Praha 6, Dejvice, CZ; ETH Zurich, 8092 Zurich, CH. Způsob využití efektů vzniklých v obrazech v důsledku relativního pohybu zařízení pro snímání obrazů vůči scéně nebo části scény a zařízení pro provádění tohoto způsobu. Inventors: Č. ALBL, et al. Czechia. Patent CZ 309023. 2021-10-20. Available from: https://isdv.upv.cz/doc/FullFiles/Patents/FullDocuments/309/309023.pdf

Conference Proceedings

MCCRAITH, R., L. NEUMANN, and A. VEDALDI. Real time monocular vehicle velocity estimation using synthetic data. In: Proceedings of 2021 IEEE Intelligent Vehicles Symposium (IV). 2021 IEEE Intelligent Vehicles Symposium (IV), Nagoya, 2021-07-11/2021-07-17. Piscataway: IEEE, 2021. p. 1406-1412. ISBN 978-1-7281-5394-0. DOI 10.1109/IV48863.2021.9575204.

PATEL, Y. and J. MATAS. FEDS -- Filtered Edit Distance Surrogate. In: ICDAR2021: 16th IAPR International Conference on Document Analysis and Recognition. Lausanne, 2021-09-05/2021-09-10. Cham: Springer International Publishing, 2021. p. 171-186. LNCS. vol. 12824. ISSN 0302-9743. ISBN 978-3-030-86336-4. DOI 10.1007/978-3-030-86337-1_12.

VOŠAHLÍK, D., et al. Self-Supervised Learning of Camera-based Drivable Surface Friction. In: ITSC 2021: IEEE Conference on Intelligent Transportation Systems. 2021 IEEE International Intelligent Transportation Systems Conference, Indianapolis, 2021-09-19/2021-09-22. Piscataway: IEEE, 2021. p. 2773-2780. ISBN 978-1-7281-9142-3. DOI 10.1109/ITSC48978.2021.9564894.

DJUKANOVIC, S., et al. Neural network-based acoustic vehicle counting. In: 29th European Signal Processing Conference (EUSIPCO). Dublin (virtual), 2021-08-23/2021-08-27. New Jersey: IEEE Signal Processing Society, 2021. p. 561-565. ISSN 2076-1465. ISBN 9789082797060. DOI 10.23919/EUSIPCO54536.2021.9615925. Available from: https://ieeexplore.ieee.org/document/9615925

KRISTAN, M., et al. The Ninth Visual Object Tracking VOT2021 Challenge Results. In: ICCVW2021: The Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. ICCV2021: IEEE International Conference on Computer Vision, Montreal, 2021-10-11/2021-10-17. New York: IEEE, 2021. p. 2711-2738. ISSN 2473-9944. ISBN 978-1-6654-0191-3. DOI 10.1109/ICCVW54120.2021.00305. Available from: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9607833

VOJÍŘ, T., I. BUDVYTIS, and R. CIPOLLA. Efficient Large-Scale Semantic Visual Localization in 2D Maps. In: ISHIKAWA, H., et al., eds. ACCV2020: Proceedings of the 15th Asian Conference on Computer Vision - Part III. ACCV 2020: Proceedings of the 14th Asian Conference on Computer Vision, Kyoto, 2020-11-30/2020-12-04. Cham: Springer, 2021. p. 273-288. LNCS. vol. 12624. ISSN 0302-9743. ISBN 978-3-030-69534-7. DOI 10.1007/978-3-030-69535-4_17.

QIAN, Y., et al. DAL: A Deep Depth-Aware Long-term Tracker. In: 2020 25th International Conference on Pattern Recognition (ICPR). ICPR2020: 25th International Conference on Pattern Recognition, Milan, 2021-01-10/2021-01-15. Los Alamitos: IEEE Computer Society, 2021. p. 7825-7832. ISSN 1051-4651. ISBN 978-1-7281-8808-9. DOI 10.1109/ICPR48806.2021.9412984. Available from: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9412984

ŠUBRTOVÁ, A., J. ČECH, and V. FRANC. Hairstyle Transfer between Face Images. In: Proc. of the 16th IEEE International Conference on Automatic Face and Gesture Recognition, 2021 (FG 2021). 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), Jodhpur, 2021-12-15/2021-12-18. Los Alamitos: IEEE Computer Society Press, 2021. ISBN 978-1-6654-3176-7. DOI 10.1109/FG52635.2021.9667038. Available from: https://ieeexplore.ieee.org/document/9667038

QIAN, Y., et al. Fast Fourier Intrinsic Network. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, 2021-01-05/2021-01-09. USA: IEEE Computer Society, 2021. p. 3168-3177. ISBN 978-0-7381-4266-1. DOI 10.1109/WACV48630.2021.00321. Available from: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9423230

KRÁLÍČEK, J. and J. MATAS. Fast Text vs. Non-text Classification of Images. In: ICDAR2021: 16th IAPR International Conference on Document Analysis and Recognition. Lausanne, 2021-09-05/2021-09-10. Cham: Springer International Publishing, 2021. p. 18-32. LNCS. vol. 12824. ISSN 0302-9743. ISBN 978-3-030-86336-4. DOI 10.1007/978-3-030-86337-1_2.

ROZUMNYI, D., et al. FMODetect: Robust Detection of Fast Moving Objects. In: ICCV2021: Proceedings of the International Conference on Computer Vision. ICCV2021: IEEE International Conference on Computer Vision, Montreal, 2021-10-11/2021-10-17. Piscataway: IEEE, 2021. p. 3521-3529. ISSN 2380-7504. ISBN 978-1-6654-2812-5. DOI 10.1109/ICCV48922.2021.00352. Available from: https://openaccess.thecvf.com/content/ICCV2021/html/Rozumnyi_FMODetect_Robust_Detection_of_Fast_Moving_Objects_ICCV_2021_paper.html

DING, Y., D. BARÁTH, and Z. KÚKELOVÁ. Homography-based Egomotion Estimation Using Gravity and SIFT Features. In: ACCV 2020: Proceedings of the 14th Asian Conference on Computer Vision, Part I. ACCV 2020: Proceedings of the 14th Asian Conference on Computer Vision, Kyoto, 2020-11-30/2020-12-04. Cham: Springer, 2021. p. 278-294. LNCS. vol. 12622. ISSN 0302-9743. ISBN 978-3-030-69524-8. DOI 10.1007/978-3-030-69525-5_17.

VOJÍŘ, T., et al. Road Anomaly Detection by Partial Image Reconstruction with Segmentation Coupling. In: ICCV2021: Proceedings of the International Conference on Computer Vision. ICCV2021: IEEE International Conference on Computer Vision, Montreal, 2021-10-11/2021-10-17. Piscataway: IEEE, 2021. p. 15651-15660. ISSN 2380-7504. ISBN 978-1-6654-2812-5. DOI 10.1109/ICCV48922.2021.01536. Available from: https://openaccess.thecvf.com/content/ICCV2021/papers/Vojir_Road_Anomaly_Detection_by_Partial_Image_Reconstruction_With_Segmentation_Coupling_ICCV_2021_paper.pdf

SHEKHOVTSOV, O. Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators. In: Proceedings of the 43rd DAGM German Conference (DAGM GCPR 2021). GCPR 2021: German Conference on Pattern Recognition DAGM, Bonn, 2021-09-28/2021-10-01. Cham: Springer, 2021. p. 127-141. LNCS. vol. 13024. ISSN 0302-9743. ISBN 978-3-030-92658-8. DOI 10.1007/978-3-030-92659-5_8.

NEORAL, M., J. ŠOCHMAN, and J. MATAS. Monocular Arbitrary Moving Object Discovery and Segmentation. In: BMVC2021: The Proceedings of the 32nd British Machine Vision Conference. BMVC2021: The 32nd British Machine Vision Conference, Online, 2021-11-22/2021-11-25. London: British Machine Vision Association, 2021. Available from: https://www.bmvc2021-virtualconference.com/assets/papers/1500.pdf

PATEL, Y., S. APPALARAJU, and R. MANMATHA. Saliency Driven Perceptual Image Compression. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). Waikoloa, HI, 2021-01-05/2021-01-09. New York: Institute of Electrical and Electronics Engineers, 2021. p. 227-236. ISBN 978-0-7381-4266-1. DOI 10.1109/WACV48630.2021.00027. Available from: https://ieeexplore.ieee.org/document/9423363

ROZUMNYI, D., et al. DeFMO: Deblurring and Shape Recovery of Fast Moving Objects. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2021-06-20/2021-06-25. USA: IEEE Computer Society, 2021. p. 3455-3464. ISSN 2575-7075. ISBN 978-1-6654-4509-2. DOI 10.1109/CVPR46437.2021.00346. Available from: https://ieeexplore.ieee.org/document/9577579

SHEKHOVTSOV, O. and V. YANUSH. Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks. In: Proceedings of the 43rd DAGM German Conference (DAGM GCPR 2021). GCPR 2021: German Conference on Pattern Recognition DAGM, Bonn, 2021-09-28/2021-10-01. Cham: Springer, 2021. p. 111-126. LNCS. vol. 13024. ISSN 0302-9743. ISBN 978-3-030-92658-8. DOI 10.1007/978-3-030-92659-5_7.

CHAMIDULLIN, R., et al. A deep learning method for visual recognition of snake species. In: Proceedings of the 2021 Working Notes of CLEF - Conference and Labs of the Evaluation Forum. CLEF2021 - Conference and Labs of the Evaluation Forum, Bucharest, 2021-09-21/2021-09-24. CEUR Workshop Proceedings, 2021. p. 1512-1525. CEUR Workshop Proceedings. vol. 2936. ISSN 1613-0073. Available from: http://ceur-ws.org/Vol-2936/paper-128.pdf

HUYNH, L., et al. Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion. In: ICCV2021: Proceedings of the International Conference on Computer Vision. ICCV2021: IEEE International Conference on Computer Vision, Montreal, 2021-10-11/2021-10-17. Piscataway: IEEE, 2021. p. 12747-12756. ISSN 2380-7504. ISBN 978-1-6654-2812-5. DOI 10.1109/ICCV48922.2021.01253. Available from: https://openaccess.thecvf.com/content/ICCV2021/papers/Huynh_Boosting_Monocular_Depth_Estimation_With_Lightweight_3D_Point_Fusion_ICCV_2021_paper.pdf

BHAYANI, S., Z. KÚKELOVÁ, and J. HEIKKILÄ. Computing stable resultant-based minimal solvers by hiding a variable. In: 2020 25th International Conference on Pattern Recognition (ICPR). ICPR2020: 25th International Conference on Pattern Recognition, Milan, 2021-01-10/2021-01-15. Los Alamitos: IEEE Computer Society, 2021. p. 6104-6111. ISSN 1051-4651. ISBN 978-1-7281-8808-9. DOI 10.1109/ICPR48806.2021.9411957. Available from: https://ieeexplore.ieee.org/document/9411957

ČECH, J., et al. Self-Supervised Learning of Camera-based Drivable Surface Roughness. In: Proceedings of 2021 IEEE Intelligent Vehicles Symposium (IV). 2021 IEEE Intelligent Vehicles Symposium (IV), Nagoya, 2021-07-11/2021-07-17. Piscataway: IEEE, 2021. p. 1319-1325. ISBN 978-1-7281-5394-0. DOI 10.1109/IV48863.2021.9575288. Available from: https://ieeexplore.ieee.org/document/9575288

GAL, I.G., D. BARÁTH, and L. HAJDER. Pose Estimation for Vehicle-mounted Cameras via Horizontal and Vertical Planes. In: IEEE International Conference on Robotics and Automation (ICRA). 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi’an, 2021-05-30/2021-06-05. IEEE Xplore, 2021. p. 7620-7626. ISSN 2577-087X. ISBN 978-1-7281-9077-8. DOI 10.1109/ICRA48506.2021.9561890. Available from: https://ieeexplore.ieee.org/document/9561890

JANOUŠKOVÁ, K., et al. Text Recognition - Real World Data and Where to Find Them. In: 2020 25th International Conference on Pattern Recognition (ICPR). ICPR2020: 25th International Conference on Pattern Recognition, Milan, 2021-01-10/2021-01-15. Los Alamitos: IEEE Computer Society, 2021. p. 4489-4496. ISSN 1051-4651. ISBN 978-1-7281-8808-9. DOI 10.1109/ICPR48806.2021.9412868. Available from: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9412868

HUYNH, L., et al. Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss. In: 3DV 2021: Proceedings of the International Conference on 3D Vision. 3DV 2021: International Conference on 3D Vision, Virtual, 2021-12-01/2021-12-03. Los Alamitos, CA: IEEE Computer Soc., 2021. p. 228-238. ISSN 2475-7888. ISBN 978-1-6654-2688-6. DOI 10.1109/3DV53792.2021.00033. Available from: https://ieeexplore.ieee.org/document/9665936

PAVLÍN, T., J. ČECH, and J. MATAS. Ballroom Dance Recognition from Audio Recordings. In: 2020 25th International Conference on Pattern Recognition (ICPR). ICPR2020: 25th International Conference on Pattern Recognition, Milan, 2021-01-10/2021-01-15. Los Alamitos: IEEE Computer Society, 2021. p. 2142-2149. ISSN 1051-4651. ISBN 978-1-7281-8808-9. DOI 10.1109/ICPR48806.2021.9412255. Available from: https://ieeexplore.ieee.org/document/9412255

DING, Y., et al. Globally Optimal Relative Pose Estimation With Gravity Prior. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2021-06-20/2021-06-25. USA: IEEE Computer Society, 2021. p. 394-403. ISSN 2575-7075. ISBN 978-1-6654-4509-2. DOI 10.1109/CVPR46437.2021.00046. Available from: https://openaccess.thecvf.com/content/CVPR2021/html/Ding_Globally_Optimal_Relative_Pose_Estimation_With_Gravity_Prior_CVPR_2021_paper.html

BARÁTH, D., et al. Efficient Initial Pose-Graph Generation for Global SfM. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2021-06-20/2021-06-25. USA: IEEE Computer Society, 2021. p. 14541-14550. ISSN 2575-7075. ISBN 978-1-6654-4509-2. DOI 10.1109/CVPR46437.2021.01431. Available from: https://openaccess.thecvf.com/content/CVPR2021/html/Barath_Efficient_Initial_Pose-Graph_Generation_for_Global_SfM_CVPR_2021_paper.html

LIVOCHKA, A. and O. SHEKHOVTSOV. Initialization and Transfer Learning of Stochastic Binary Networks from Real-Valued Ones. In: 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021). 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2021-06-20/2021-06-25. New York: IEEE Computer Society Press, 2021. p. 4655-4663. ISSN 2160-7516. ISBN 978-1-6654-4899-4. DOI 10.1109/CVPRW53098.2021.00524. Available from: https://ieeexplore.ieee.org/document/9522752

NGUYEN, P., et al. RGBD-Net: Predicting Color and Depth Images for Novel Views Synthesis. In: 3DV 2021: Proceedings of the International Conference on 3D Vision. 3DV 2021: International Conference on 3D Vision, Virtual, 2021-12-01/2021-12-03. Los Alamitos, CA: IEEE Computer Soc., 2021. p. 1095-1105. ISSN 2475-7888. ISBN 978-1-6654-2688-6. DOI 10.1109/3DV53792.2021.00117. Available from: https://ieeexplore.ieee.org/document/9665841

NEUMANN, L. and A. VEDALDI. Pedestrian and Ego-vehicle Trajectory Prediction from Monocular Camera. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2021-06-20/2021-06-25. USA: IEEE Computer Society, 2021. p. 10199-10207. ISSN 2575-7075. ISBN 978-1-6654-4509-2. DOI 10.1109/CVPR46437.2021.01007. Available from: https://ieeexplore.ieee.org/document/9577864

BARÁTH, D., et al. Image Stitching with Locally Shared Rotation Axis. In: 3DV 2021: Proceedings of the International Conference on 3D Vision. 3DV 2021: International Conference on 3D Vision, Virtual, 2021-12-01/2021-12-03. Los Alamitos, CA: IEEE Computer Soc., 2021. p. 1382-1391. ISSN 2475-7888. ISBN 978-1-6654-2688-6. DOI 10.1109/3DV53792.2021.00145. Available from: https://ieeexplore.ieee.org/abstract/document/9665873

DING, Y., D. BARÁTH, and Z. KÚKELOVÁ. Minimal solutions for panoramic stitching given gravity prior. In: ICCV2021: Proceedings of the International Conference on Computer Vision. ICCV2021: IEEE International Conference on Computer Vision, Montreal, 2021-10-11/2021-10-17. Piscataway: IEEE, 2021. p. 5579-5588. ISSN 1550-5499. ISBN 978-1-6654-2813-2. DOI 10.1109/ICCV48922.2021.00553.

BHAYANI, S., et al. Calibrated and Partially Calibrated Semi-Generalized Homographies. In: ICCV2021: Proceedings of the International Conference on Computer Vision. ICCV2021: IEEE International Conference on Computer Vision, Montreal, 2021-10-11/2021-10-17. Piscataway: IEEE, 2021. p. 5916-5925. ISSN 2380-7504. ISBN 978-1-6654-2812-5. DOI 10.1109/ICCV48922.2021.00588. Available from: https://openaccess.thecvf.com/content/ICCV2021/papers/Bhayani_Calibrated_and_Partially_Calibrated_Semi-Generalized_Homographies_ICCV_2021_paper.pdf

IVASHECHKIN, M., D. BARÁTH, and J. MATAS. VSAC: Efficient and Accurate Estimator for H and F. In: ICCV2021: Proceedings of the International Conference on Computer Vision. ICCV2021: IEEE International Conference on Computer Vision, Montreal, 2021-10-11/2021-10-17. Piscataway: IEEE, 2021. p. 15223-15232. ISSN 2380-7504. ISBN 978-1-6654-2812-5. DOI 10.1109/ICCV48922.2021.01496. Available from: https://ieeexplore.ieee.org/document/9710283

Dissertations

MISHKIN, D. Learning and Crafting for the Wide Multiple Baseline Stereo. Defense date 2021-12-16. PhD Thesis. CTU FEE. Visual Recognition Group.

HODAŇ, T. Pose Estimation of Specific Rigid Objects. Praha: Defense date 2021-07-07. PhD Thesis. CTU FEE. Department of Cybernetics. Supervised by J. MATAS.

Research Reports

BELLAVIA, F. and D. MISHKIN. HarrisZ+: Harris corner selection for next-gen image matching pipelines. [Research Report] 2021.

DOUZE, M., et al. The 2021 Image Similarity Dataset and Challenge. [Research Report] ArXiv, 2021.

PATEL, Y., G. TOLIAS, and J. MATAS. Recall@k Surrogate Loss with Large Batches and Similarity Mixup. [Research Report] ArXiv, 2021.