Tomasz Trzciński, DSc, PhD

Associate Professor, Warsaw University of Technology

Polski

Biography

Tomasz Trzciński (DSc, WUT'20; PhD, EPFL'14; MSc, UPC/PoliTo'10) is an Associate Professor at Warsaw University of Technology, where he leads a Computer Vision Lab, and at Jagiellonian University of Cracow (GMUM). He was a Visiting Scholar at Stanford University in 2017 and at Nanyang Technological University in 2019. Previously, he worked at Google in 2013, Qualcomm in 2012 and Telefónica in 2010. He is an Associate Editor of IEEE Access and MDPI Electronics and frequently serves as a reviewer in major computer science conferences (CVPR, ICCV, ECCV, NeurIPS, ICML) and journals (TPAMI, IJCV, CVIU). He is a Senior Member of IEEE, member of ELLIS, member of the ALICE Collaboration at CERN and an expert of National Science Centre and Foundation for Polish Science. He is a Chief Scientist at Tooploox and a co-founder of Comixify, a technology startup focused on using machine learning algorithms for video editing.

Research interests: computer vision (SLAM, visual search), machine learning (deep learning, generative models, continual learning), representation learning (binary descriptors).

Contact details

address: ul. Nowowiejska 15/19, 00-665 Warsaw, Poland
email: tomasz.trzcinski@pw.edu.pl
tel: +48 22 234 7650
office hours: online after email contact

Publications

Selected journal papers:

  • J. Komorowski, M. Wysoczanska, T. Trzcinski. EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale, IEEE Robotics and Automation Letters, 2021. arXiv
  • P. Spurek, M. Zięba, J. Tabor, T. Trzcinski. General hypernetwork framework for creating 3D point clouds, IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2021.
  • M. Stypułkowski, K. Kania, M. Zamorski, M. Zięba, T. Trzcinski, J. Chorowski. Representing point clouds with generative conditional invertible flow networks, Pattern Recognition Letters, Vol. 150, p. 26-32, 2021. pdf
  • K. Deja, J. Dubinski, P. Nowak, S. Wenzel, P. Spurek, T. Trzcinski. End-to-end Sinkhorn Autoencoder with Noise Generator. IEEE Access, 2021. pdf
  • M. Zamorski, M. Zieba, P. Klukowski, R. Nowak, K. Kurach, W. Stokowiec, T. Trzcinski. Adversarial autoencoders for compact representations of 3D point clouds, Computer Vision and Image Understanding, 2020. arXiv
  • I. Tautkute, T. Trzcinski, A. Skorupa, L. Brocki, K. Marasek. DeepStyle: Multimodal Search Engine for Fashion and Interior Design. IEEE Access, Vol. 6, Nr. 1, p. 84613-84628, 2019. pdf
  • M. Komorowski, T. Trzcinski. Random Binary Search Trees for approximate nearest neighbour search in binary spaces, Applied Soft Computing, Vol. 79, p. 87-93, 2019. official version
  • A. Bielski, T. Trzcinski. Understanding Multimodal Popularity Prediction of Social Media Videos with Self-Attention. IEEE Access, Vol. 6, Nr. 1, p. 74277-74287, 2018. pdf
  • T. Trzcinski, P. Rokita. Predicting popularity of online videos using Support Vector Regression. IEEE Trans. Multimedia (TMM). Vol. 19, Nr. 11, p. 2561-2570, 2017. arXiv
  • T. Trzcinski, M. Christoudias, V. Lepetit. Learning Image Descriptors with Boosting. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI). Vol. 37, Nr. 3, pp. 597-610, 2015. pdf
  • B. Fan, Q. Kong, T. Trzcinski, Z. Wang, C. Pan, P. Fua. Receptive Fields Selection for Binary Feature Description. IEEE Trans. Image Processing (TIP). Vol. 23, Nr. 6, pp. 2583-2595, 2014. official version
  • T. Trzcinski, V. Lepetit, P. Fua. Thick Boundaries in Binary Space and their Influence on Nearest-Neighbor Search. Pattern Recognition Letters (PRL). Vol. 33, pp. 2173-2180, 2012. pdf, code
  • M. Calonder, V. Lepetit, M. Ozuysal, T. Trzcinski, C. Strecha, P. Fua. BRIEF: Computing a local binary descriptor very fast. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI). Vol. 34, Nr. 7, pp. 1281 - 1298, 2012. pdf

Selected conference papers:

  • M. Wołczyk, K. Piczak, B. Wójcik, Ł. Pustelnik, P. Morawiecki, J. Tabor, T. Trzcinski, P. Spurek. Continual Learning with Guarantees via Weight Interval Constraints, International Conference on Machine Learning (ICML), 2022.
  • S. Plotka, M. Grzeszczyk, R. Samaha, P. Gutaj, M. Lipa, T. Trzciński, A. Sitek. BabyNet: Residual Transformer Module for Birth Weight Prediction on Fetal Ultrasound Video. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2022.
  • K. Deja, P. Wawrzynski, W. Masarczyk, D. Marczak, T. Trzcinski. Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning. International Joint Conference on Artificial Intelligence (IJCAI), 2022. arXiv
  • K. Kania, K. Moo Yi, M. Kowalski, T. Trzcinski, A. Tagliasacchi. CoNeRF: Controllable Neural Radiance Fields. Computer Vision and Pattern Recognition (CVPR), 2022. arXiv
  • M. Wolczyk, B. Wójcik, K. Bałazy, I. Podolak, J. Tabor, M. Śmieja, T. Trzcinski. Zero Time Waste: Recycling Predictions in Early Exit Neural Networks, Neural Information Processing Systems (NeurIPS), 2021. arXiv
  • M. Sendera, J. Tabor, A. Nowak, A. Bedychaj, M. Patacchiola, T. Trzcinski, P. Spurek, M. Zieba. Non-Gaussian Gaussian Processes for Few-Shot Regression, Neural Information Processing Systems (NeurIPS), 2021. arXiv
  • W. Masarczyk, K. Deja, T. Trzcinski. On robustness of generative representations against catastrophic forgetting, International Conference on Neural Information Processing (ICONIP), 2021. arXiv
  • M. Sadowski, K. Piczak, P. Spurek, T. Trzcinski. Continual Learning of 3D Point Cloud Generators, International Conference on Neural Information Processing (ICONIP), 2021.
  • D. Basaj, W. Oleszkiewicz, I. Sieradzki, M. Górszczak, B. Rychalska, T. Trzcinski, B. Zielinski. Explaining Self-Supervised Image Representations with Visual Probing, International Joint Conference on Artificial Intelligence (IJCAI), 2021. pdf
  • P. Spurek, S. Winczowski, J. Tabor, M. Zamorski, M. Zięba, T. Trzcinski. Hypernetwork approach to generating point clouds, International Conference on Machine Learning (ICML), 2020. arXiv
  • M. Koperski, T. Konopczyński, P. Semberecki, R. Nowak, T. Trzcinski. Plugin Networks for Inference under Partial Evidence, IEEE Workshop on Applications of Computer Vision (WACV), 2020. arXiv
  • M. Zieba, P. Semberecki, T. El-Gaaly, T. Trzcinski. BinGAN: Learning Compact Binary Descriptors with a Regularized GAN. Neural Information Processing Systems (NeurIPS), 2018. arXiv
  • N. Kapinski, J. Zielinski, B. Borucki, T. Trzcinski, B. Ciszkowska-Lyson, K. Nowinski. Estimating Achilles tendon healing progress with convolutional neural networks. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2018. arXiv
  • M. Kowalski, J. Naruniec, T. Trzcinski. Deep Alignment Network: A convolutional neural network for robust face alignment. Computer Vision and Pattern Recognition (CVPR), Face Detection in the Wild Workshop, 2017. arXiv
  • T. Trzcinski, M. Christoudias, P. Fua, V. Lepetit. Boosting Binary Keypoint Descriptors. Computer Vision and Pattern Recognition (CVPR), 2013. pdf, code
  • T. Trzcinski, M. Christoudias, V. Lepetit, P. Fua. Learning Image Descriptors with the Boosting-Trick. Neural Information Processing Systems (NIPS), 2012. pdf
  • T. Trzcinski, V. Lepetit. Efficient Discriminative Projections for Compact Binary Descriptors. European Conference on Computer Vision (ECCV), 2012. pdf, code
Google Scholar Profile

Media coverage

Funding

  • PRELUDIUM BIS 3/ST6: Continual self-supervised representation learning, 2022-2026.
  • OPUS 20/ST6: Deep generative view on continual learning, 2021-2024.
  • Microsoft Research PhD Scholarship Award: Low Shot Realistic Human Rendering from Partial Information, 2020-2023.
  • Grant of Priority Research Domain at WUT - Artificial Intelligence and Robotics: Binary representations and their application in continual learning, 2020-2021.
  • Grant of Priority Research Domain at WUT - High Energy Physics and Experimantal Techniques: WUT@ALICE: Study of fundamental properties of strongly interacting matter with particle correlations and machine learning in ALICE at LHC, 2020-2021.
  • Grant of Scientific Discipline of Computer Science and Telecommunications at WUT: Spontanuous preterm birth prediction based on ultrasound data using machine learning methods, 2020-2021.
  • FNP TEAM-NET (UJ): Bio-inspired artificial neural networks, 2019-2023. project website
  • Google Project ARCore: Hierarchical visual representations for visual localization, 2019-2020.
  • Dean's grant: Preterm birth prediction based on ultrasound images using artificial neural networks, 2019.
  • Google Project ARCore: Improving stability of keypoint detection using deep neural networks, 2018-2019.
  • Dean's grant: Online social media video classification with deep neural networks, 2017.
  • SONATA 11/ST6: The development of machine learning methods for big data quality monitoring and its interactive visualisation in the frames of the ALICE experiment at the Large Hadron Collider at CERN, 2016-2019.
  • Google Project Tango: Efficient and accurate nearest-neighbor search for binary local feature descriptors, 2016-2017.
  • Dean's grant: Application of artificial intelligence algorithms for the analysis of viral videos' phenomenon, 2015.

Teaching

  • Introduction to Artificial Intelligence: PW, since 2017.
  • Digital Image Processing: PW, since 2015.
  • Algorithm Analysis: PW, since 2015.
  • Foundations of Imaging Science: EPFL, 2011-2013.
Copyright © black_white