Tomasz Trzciński, PhD

Assistant Professor, Warsaw University of Technology

Polski

Biography

Tomasz Trzciński is an Assistant Professor in the Division of Computer Graphics in the Institute of Computer Science at Warsaw University of Technology since 2015. He obtained his Ph.D. in Computer Vision at École Polytechnique Fédérale de Lausanne in 2014. He received his M.Sc. degree in Research on Information and Communication Technologies from Universitat Politècnica de Catalunya and M.Sc. degree in Electronics Engineering from Politecnico di Torino in 2010. He has (co)-authored several papers in top-tier computer science conferences (CVPR, ECCV, NIPS) and high impact factor journals (TPAMI, TIP, TMM, PRL). He frequently serves as a reviewer in major computer vision conferences (CVPR, ICCV, ECCV, BMVC) and international journals (TPAMI, VISI, CVIU, TCSVT). His professional appointments include work with Google in 2013, Qualcomm Corporate R&D in 2012 and Telefónica R&D in 2010. In 2017, he was appointed a Visiting Scholar at Stanford University. In 2016, he was named New Europe 100 Innovator as one of 100 outstanding challengers who are leading world-class innovation from Central and Eastern Europe. Since 2015, he holds a Chief Scientist position at Tooploox where he leads a team of data scientists.

Research interests: video content analysis, computer vision, visual content search, augmented reality, machine learning, deep learning, neural networks, online content popularity prediction, social media, medical image processing.

Contact details

address: ul. Nowowiejska 15/19, 00-665 Warsaw, Poland
email: t.trzcinski@ii.pw.edu.pl
tel: +48 22 234 7650
office hours: Tuesday, 2pm-4pm, office 415A

Publications

Journals:

  • 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

Conferences:

  • M. Zieba, P. Semberecki, T. El-Gaaly, T. Trzcinski. BinGAN: Learning Compact Binary Descriptors with a Regularized GAN. International Conference on Machine Learning (ICML), Workshop on Theoretical Foundations and Applications of Deep Generative Models, 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
  • A. Bielski, T. Trzcinski. Pay Attention to Virality: understanding popularity of social media videos with the attention mechanism. Computer Vision and Pattern Recognition (CVPR), Understanding Subjective Attributes of Data Workshop, 2018 (oral presentation). arXiv
  • I. Tautkute, T. Trzcinski, A. Bielski. I Know How You Feel: Emotion Recognition with Facial Landmarks. Computer Vision and Pattern Recognition (CVPR), Women in Computer Vision Workshop, 2018. arXiv
  • W. Oleszkiewicz, T. Wlodarczyk, K. Piczak, T. Trzcinski, P. Kairouz, R. Rajagopal. Siamese Generative Adversarial Privatizer for Biometric Data. Computer Vision and Pattern Recognition (CVPR), Workshop on the Bright and Dark Sides of Computer Vision, 2018. arXiv
  • J. Komorowski, T. Trzcinski. Aggregation of binary feature descriptors for compact scene model representation in large scale structure-from-motion applications. International Conference on Computer Vision and Graphics (ICCVG), 2018.
  • A. Slucki, T. Trzcinski, A. Bielski, P. Cyrta. Extracting textual overlays from social media videos using neural networks. International Conference on Computer Vision and Graphics (ICCVG), 2018. arXiv
  • T. Trzcinski, M. Glinka, Ł. Graczykowski for the ALICE Collaboration. Using Random Forest Classifier for particle identification in the ALICE Experiment. Conference on Information Technology, Systems Research and Computational Physics (ITSRCP), 2018. pdf
  • K. Deja, T. Trzcinski, Ł. Graczykowski for the ALICE Collaboration. Generative Models for Fast Cluster Simulations in the TPC for the ALICE Experiment. Conference on Information Technology, Systems Research and Computational Physics (ITSRCP), 2018. pdf
  • P. Nowakowski, J. Myrcha, T. Trzcinski, Ł. Graczykowski, P. Rokita for the ALICE Collaboration. Comparison of 3D graphics engines for particle track visualization in the ALICE Experiment. Conference on Information Technology, Systems Research and Computational Physics (ITSRCP), 2018. pdf
  • I. Tautkute, T. Trzcinski, A. Bielski. Recognizing Emotions with EmotionalDAN. International Symposium on Computational Modeling of Objects Presented in Images (CompIMAGE), 2018.
  • T. Trzcinski, A. Bielski, P. Cyrta, M. Zak. SocialML: machine learning for social media video creators. Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Creativity and Design, 2017. arXiv
  • T. Trzcinski, P. Andruszkiewicz, T. Bocheński, P. Rokita. Recurrent Neural Networks for Online Video Popularity Prediction. International Symposium on Methodologies for Intelligent Systems (ISMIS), 2017. arXiv
  • W. Stokowiec, T. Trzcinski, K. Wolk, K. Marasek, P. Rokita. Shallow reading with Deep Learning: Predicting popularity of online content using only its title. International Symposium on Methodologies for Intelligent Systems (ISMIS), 2017. 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
  • J. Myrcha, T. Trzcinski, P. Rokita. Virtual Reality Visualization Algorithms for the ALICE High Energy Physics Experiment on the LHC at CERN. IEEE-SPIE Joint Symposium on Photonics, Web Engineering, Electronics for Astronomy and High Energy Physics Experiments (WILGA), 2017. pdf
  • I. Tautkute, A. Możejko, W. Stokowiec, T. Trzcinski, Ł. Brocki, K. Marasek. What Looks Good with my Sofa: Multimodal Search Engine for Interior Design. FEDCSIS Conference on Multimedia, Interaction, Design and Innovation (MIDI), 2017. arXiv
  • M. Suchecki, T. Trzcinski. Understanding aesthetics in photography using deep convolutional neural networks. International Conference on Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2017. arXiv
  • P. Cyrta, T. Trzcinski, W. Stokowiec. Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings. International Conference on Information Systems Architecture and Technology (ISAT), 2017. arXiv
  • J. Komorowski, T. Trzcinski. Evaluation of Hashing Methods Performance on Binary Feature Descriptors. International Conference on Processing and Communications (IPC), 2017. arXiv
  • M. Komorowski, T. Trzcinski. Random Binary Trees for Approximate Nearest Neighbour Search in Binary Space. International Conference on Pattern Recognition and Machine Intelligence (PReMI), 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
  • D. Marimon, T. Adamek, A. Bonnin, T. Trzcinski. Enhancing global positioning by image recognition. International Symposium on Mixed and Augmented Reality (ISMAR), Workshop on Enabling Large-Scale Outdoor Mixed Reality and Augmented Reality, 2011. pdf

Others:

  • T. Trzcinski. Learning and Matching Binary Local Feature Descriptors. Ph.D. Thesis, EPFL, n° 6226 (2014). pdf
  • T. Trzcinski. Towards Precise Outdoor Localisation Based on Image Recognition. M.Sc. Thesis, Universitat Politècnica de Catalunya, Politecnico di Torino (2010). pdf
Google Scholar Profile

Media coverage

Funding

  • 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