13133 / 13162 - Publications - 2017

13133 / 13162 - Visual Recognition Group

Publications 2017

Papers in WoS Journals

MISHKIN, D., N. SERGIEVSKIY, and J. MATAS. Systematic Evaluation of Convolution Neural Network Advances on the ImageNet. Computer Vision and Image Understanding. 2017, 161 11-19. ISSN 1077-3142. DOI 10.1016/j.cviu.2017.05.007.

ŠULC, M. and J. MATAS. Fine-grained recognition of plants from images. Plant Methods. 2017, 13(1), ISSN 1746-4811. DOI 10.1186/s13007-017-0265-4. Available from: https://plantmethods.biomedcentral.com/articles/10.1186/s13007-017-0265-4

CHUM, O. Optimizing explicit feature maps on intervals. Image and Vision Computing. 2017, 66 36-47. ISSN 0262-8856. DOI 10.1016/j.imavis.2017.07.001.

Conference Proceedings

ISCEN, A., et al. Panorama to panorama matching for location recognition. In: ICMR '17 Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. ACM International Conference on Multimedia Retrieval, Bucharest, 2017-06-06/2017-06-09. New York: ACM, 2017. p. 392-396. ISBN 978-1-4503-4701-3. DOI 10.1145/3078971.3079033.

ŠULC, M. and J. MATAS. Learning with Noisy and Trusted Labels for Fine-Grained Plant Recognition. In: Working Notes of CLEF 2017 - Conference and Labs of the Evaluation Forum. CLEF 2017: Conference and Labs of the Evaluation Forum, Dublin, 2017-09-11/2017-09-14. Aachen: CEUR Workshop Proceedings, 2017. vol. 1866. ISSN 1613-0073. Available from: http://ceur-ws.org/Vol-1866/paper_167.pdf

KÚKELOVÁ, Z., et al. A clever elimination strategy for efficient minimal solvers. In: CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, 2017-07-21/2017-07-26. IEEE Computer Society Press, 2017. p. 3605-3614. ISSN 1063-6919. ISBN 978-1-5386-0457-1. DOI 10.1109/CVPR.2017.384.

TOLIAS, G. and O. CHUM. Asymmetric Feature Maps with Application to Sketch Based Retrieval. In: CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, 2017-07-21/2017-07-26. IEEE Computer Society Press, 2017. p. 6185-6193. ISSN 1063-6919. ISBN 978-1-5386-0457-1. DOI 10.1109/CVPR.2017.655.

KRISTAN, M., et al. The Visual Object Tracking VOT2017 challenge results. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW 2017). IEEE International Conference on Computer Vision, Venice, 2017-10-22/2017-10-29. Piscataway, NJ: IEEE, 2017. p. 1949-1972. ISSN 2473-9944. ISBN 978-1-5386-1034-3. DOI 10.1109/ICCVW.2017.230.

ALBL, Č., et al. On the Two-View Geometry of Unsynchronized Cameras. In: CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, 2017-07-21/2017-07-26. IEEE Computer Society Press, 2017. p. 5593-5602. ISSN 1063-6919. ISBN 978-1-5386-0457-1. DOI 10.1109/CVPR.2017.593.

ROZUMNYI, D., et al. The World of Fast Moving Objects. In: CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, 2017-07-21/2017-07-26. IEEE Computer Society Press, 2017. p. 4838-4846. ISSN 1063-6919. ISBN 978-1-5386-0457-1. DOI 10.1109/CVPR.2017.514.

LUKEŽIC, A.L., et al. Discriminative Correlation Filter with Channel and Spatial Reliability. In: CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, 2017-07-21/2017-07-26. IEEE Computer Society Press, 2017. p. 4847-4856. ISSN 1063-6919. ISBN 978-1-5386-0457-1. DOI 10.1109/CVPR.2017.515.

QIAN, Y., et al. Deep structured-output regression learning for computational color constancy. In: 2016 23rd International Conference on Pattern Recognition (ICPR). 2016 23rd International Conference on Pattern Recognition, Cancun, 2016-12-04/2016-12-08. Institute of Electrical and Electronics Engineers, 2017. p. 1899-1904. ISSN 1051-4651. ISBN 978-1-5090-4847-2. DOI 10.1109/ICPR.2016.7899914.

MISHCHUK, A., et al. Working hard to know your neighbor's margins: Local descriptor learning loss. In: Advances in Neural Information Processing Systems 30. Neural Information Processing Systems, LONG BEACH, 2017-12-04/2017-12-09. Neural Information Processing Systems (NIPS) Foundation, 2017. p. 4827-4838. vol. 30. ISSN 1049-5258. Available from: http://papers.nips.cc/paper/7068-working-hard-to-know-your-neighbors-margins-local-descriptor-learning-loss

MUKUNDAN, A., G. TOLIAS, and O. CHUM. Robust data whitening as an iteratively re-weighted least squares problem. In: SHARMA, P. and F. M. BIANCHI, eds. Image Analysis. 20th Scandinavian Conference, SCIA 2017, Tromsø,, Tromso, 2017-06-12/2017-06-14. Cham: Springer International Publishing, 2017. p. 234-247. Lecture Notes in Computer Science. vol. 10269. ISSN 0302-9743. ISBN 978-3-319-59125-4. DOI 10.1007/978-3-319-59126-1_20.

BUŠTA, M., L. NEUMANN, and J. MATAS. Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework. In: 2017 IEEE International Conference on Computer Vision (ICCV 2017). IEEE International Conference on Computer Vision, Venice, 2017-10-22/2017-10-29. Piscataway: IEEE, 2017. p. 2223-2231. ISSN 1550-5499. ISBN 978-1-5386-1032-9. DOI 10.1109/ICCV.2017.242.

ALDANA IUIT, J., et al. In the Saddle: Chasing fast and repeatable features. In: 2016 23rd International Conference on Pattern Recognition (ICPR). 2016 23rd International Conference on Pattern Recognition, Cancun, 2016-12-04/2016-12-08. Institute of Electrical and Electronics Engineers, 2017. p. 675-680. ISSN 1051-4651. ISBN 978-1-5090-4847-2. DOI 10.1109/ICPR.2016.7899712.

ŠMÍD, M. and J. MATAS. Rolling Shutter Camera Synchronization with Sub-millisecond Accuracy. In: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Porto, 2017-02-27/2017-03-01. Madeira: SciTePress, 2017. p. 238-245. vol. 4. ISBN 978-989-758-225-7. DOI 10.5220/0006175402380245. Available from: http://cmp.felk.cvut.cz/~smidm/rolling-shutter-camera-synchronization-with-sub-millisecond-accuracy.html

HODAŇ, T., et al. T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV). 17th IEEE Winter Conference on Applications of Computer Vision, Santa Rosa, 2017-03-24/2017-03-31. New Jersey: IEEE, 2017. p. 880-888. ISSN 2472-6737. ISBN 978-1-5090-4822-9. DOI 10.1109/WACV.2017.103.

ŠPETLÍK, R., et al. Visual Language Identification from Facial Landmarks. In: SHARMA, P. and F.M. BIANCHI, eds. Image Analysis, Part II. 20th Scandinavian Conference, SCIA 2017, Tromsø,, Tromso, 2017-06-12/2017-06-14. Springer, Cham, 2017. p. 389-400. Lecture Notes in Computer Science. vol. 10270. ISSN 0302-9743. ISBN 978-3-319-59128-5. DOI 10.1007/978-3-319-59129-2_33.

MUKUNDAN, A., G. TOLIAS, and O. CHUM. Multiple-Kernel Local-Patch Descriptor. In: 28th British Machine Vision Conference 2017 Proceedings. British Machine Vision Conference 2017, London, 2017-09-04/2017-09-07. British Machine Vision Association, 2017. ISBN 978-1-901725-60-5. DOI 10.5244/C.31.184.

MUSTANIEMI, J., et al. Inertial-Based Scale Estimation for Structure from Motion on Mobile Devices. In: Intelligent Robots and Systems (IROS), 2017 IEEE/RSJ International Conference on. IEEE/RSJ International Conference on Intelligent Robots and Systems, Vancouver, 2017-09-24/2017-09-28. Piscataway: IEEE, 2017. p. 4394-4401. ISSN 2153-0866. ISBN 978-1-5386-2682-5. DOI 10.1109/IROS.2017.8206303.

MUNDA, G., et al. Scalable full flow with learned binary descriptors. In: VETTER, T. and V. ROTH, eds. 39th German Conference on Pattern Recognition. Basel, 2017-09-12/2017-09-15. Springer, Cham, 2017. p. 321-332. Lecture Notes in Computer Science. vol. 10496. ISSN 0302-9743. ISBN 978-3-319-66708-9. DOI 10.1007/978-3-319-66709-6_26.

QIAN, Y., et al. Recurrent Color Constancy. In: 2017 IEEE International Conference on Computer Vision (ICCV 2017). IEEE International Conference on Computer Vision, Venice, 2017-10-22/2017-10-29. Piscataway: IEEE, 2017. p. 5459-5467. ISSN 1550-5499. ISBN 978-1-5386-1032-9. DOI 10.1109/ICCV.2017.582.

ISCEN, A., et al. Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations. In: CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, 2017-07-21/2017-07-26. IEEE Computer Society Press, 2017. p. 926-935. ISSN 1063-6919. ISBN 978-1-5386-0457-1. DOI 10.1109/CVPR.2017.105.

HUSÁK, P., J. ČECH, and J. MATAS. Spotting Facial Micro-Expressions “In the Wild”. In: KROPATSCH, W, I JANUSCH, and N ARTNER, eds. Proceedings of the 22nd Computer Vision Winter Workshop. CVWW 2017: COMPUTER VISION WINTER WORKSHOP, Retz, 2017-02-06/2017-02-08. Wien: Pattern Recognition & Image Processing Group, Vienna University of Technology, 2017. ISBN 978-3-200-04969-7. Available from: http://cvww2017.prip.tuwien.ac.at/papers/CVWW2017_paper_17.pdf

NEORAL, M. and J. ŠOCHMAN. Object Scene Flow with Temporal Consistency. In: KROPATSCH, W, I JANUSCH, and N ARTNER, eds. Proceedings of the 22nd Computer Vision Winter Workshop. CVWW 2017: COMPUTER VISION WINTER WORKSHOP, Retz, 2017-02-06/2017-02-08. Wien: Pattern Recognition & Image Processing Group, Vienna University of Technology, 2017. ISBN 978-3-200-04969-7.

LARSSON, V., Z. KÚKELOVÁ, and Y. ZHENG. Making Minimal Solvers for Absolute Pose Estimation Compact and Robust. In: 2017 IEEE International Conference on Computer Vision (ICCV 2017). IEEE International Conference on Computer Vision, Venice, 2017-10-22/2017-10-29. Piscataway: IEEE, 2017. p. 2335-2343. ISSN 1550-5499. ISBN 978-1-5386-1032-9. DOI 10.1109/ICCV.2017.254.

GALUŠČÁKOVÁ, P, et al. Visual Descriptors in Methods for Video Hyperlinking. In: ICMR '17 Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. ACM International Conference on Multimedia Retrieval, Bucharest, 2017-06-06/2017-06-09. New York: ACM, 2017. p. 294-300. ISBN 978-1-4503-4701-3. DOI 10.1145/3078971.3079026.

FRANC, V. and J. ČECH. Learning CNNs for face recognition from weakly annotated images. In: International Conference on Automatic Face and Gesture Recognition Workshops, Biometrics in the Wild. The 12th IEEE International Conference on Automatic Face and Gesture Recognition, Washington DC, 2017-05-30/2017-06-03. USA: IEEE Computer Society, 2017. p. 933-940. ISSN 2326-5396. ISBN 978-1-5090-4023-0. DOI 10.1109/FG.2017.115. Available from: ftp://cmp.felk.cvut.cz/pub/cmp/articles/franc/Franc-EMSVM-FG2017.pdf

Dissertations

NEUMANN, L. Scene text localization and recognition in images and videos. Praha: Defense date 2017-11-24. PhD Thesis. ČVUT FEL, Katedra kybernetiky - Centrum strojového vnímání. Supervised by J. MATAS.

Research Reports

MISHCHUK, A., et al. Working hard to know your neighbor's margins: Local descriptor learning loss. [Research Report] ArXiv, 2017.

VOJÍŘ, T. and J. MATAS. Pixel-Wise Object Segmentations for the {VOT} 2016 Dataset. [Research Report] Praha: ČVUT FEL, Katedra kybernetiky - Centrum strojového vnímání, 2017. Report no. CTU--CMP--2017--01. ISSN 1213-2365.

RADENOVIĆ, F., G. TOLIAS, and O. CHUM. Deep Shape Matching. [Research Report] ArXiv, 2017. Report no. arXiv:1709.03409.

KUPYN, O., et al. DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks. [Research Report] ArXiv, 2017.

MISHKIN, D., F. RADENOVIĆ, and J. MATAS. Repeatability Is Not Enough: Learning Affine Regions via Discriminability. [Research Report] ArXiv, 2017.

RADENOVIĆ, F., G. TOLIAS, and O. CHUM. Fine-tuning CNN Image Retrieval with No Human Annotation. [Research Report] ArXiv, 2017. Report no. arXiv:1711.02512.

ISCEN, A., et al. Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations. [Research Report] ArXiv, 2017. Report no. arXiv:1611.05113.

The page was created 03.12.2024 05:00:01
Responsible person: RNDr. Patrik Mottl, Ph.D.