Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Petr Sojka

Petr Sojka

Faculty of Informatics Masaryk University

WebMIaS on Docker: Deploying Math-Aware Search in a Single Line of Code


Jun 01, 2021
Dávid Lupták, Vít Novotný, Michal Štefánik, Petr Sojka

Figure 1 for WebMIaS on Docker: Deploying Math-Aware Search in a Single Line of Code
Figure 2 for WebMIaS on Docker: Deploying Math-Aware Search in a Single Line of Code
Figure 3 for WebMIaS on Docker: Deploying Math-Aware Search in a Single Line of Code
Figure 4 for WebMIaS on Docker: Deploying Math-Aware Search in a Single Line of Code
* Accepted to be published in: Intelligent Computer Mathematics 14th International Conference, CICM 2021, Timisoara, Romania, July 26--31, 2021, Proceedings, Fairouz Kamareddine and Claudio Sacerdotti-Coen (eds.), Lecture Notes in Artificial Intelligence, Springer, Cham, 2021 
  Access Paper or Ask Questions

When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting


Apr 21, 2021
Vít Novotný, Michal Štefánik, Eniafe Festus Ayetiran, Petr Sojka

Figure 1 for When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
Figure 2 for When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
Figure 3 for When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
Figure 4 for When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting

  Access Paper or Ask Questions

EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses


Feb 27, 2021
Eniafe Festus Ayetiran, Petr Sojka, VĂ­t NovotnĂ˝

Figure 1 for EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
Figure 2 for EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
Figure 3 for EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
Figure 4 for EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
* Knowledge-Based Systems. 219 (2021) 106902 
  Access Paper or Ask Questions

One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages


Feb 04, 2021
Vít Novotný, Eniafe Festus Ayetiran, Dávid Lupták, Michal Štefánik, Petr Sojka

Figure 1 for One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages
Figure 2 for One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages
Figure 3 for One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages
Figure 4 for One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages

  Access Paper or Ask Questions

Text classification with word embedding regularization and soft similarity measure


Mar 10, 2020
Vít Novotný, Eniafe Festus Ayetiran, Michal Štefánik, Petr Sojka

Figure 1 for Text classification with word embedding regularization and soft similarity measure

  Access Paper or Ask Questions

Gait Recognition from Motion Capture Data


Aug 24, 2017
Michal Balazia, Petr Sojka

Figure 1 for Gait Recognition from Motion Capture Data
Figure 2 for Gait Recognition from Motion Capture Data
Figure 3 for Gait Recognition from Motion Capture Data
Figure 4 for Gait Recognition from Motion Capture Data
* Preprint. Full paper accepted at the ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), special issue on Representation, Analysis and Recognition of 3D Humans. 18 pages. arXiv admin note: substantial text overlap with arXiv:1701.00995, arXiv:1609.04392, arXiv:1609.06936 
  Access Paper or Ask Questions

An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods


Aug 24, 2017
Michal Balazia, Petr Sojka

Figure 1 for An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods
Figure 2 for An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods
Figure 3 for An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods
Figure 4 for An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods
* Preprint. Full paper published at the 1st IAPR Workshop on Proceedings of Reproducible Research in Pattern Recognition, RRPR 2016, Cancun, Mexico, Dec 2016. Springer, LNCS, Volume 10214, pp. 33-47, 2017. DOI: 10.1007/978-3-319-56414-2_3. arXiv admin note: text overlap with arXiv:1609.06936, arXiv:1609.04392 
  Access Paper or Ask Questions

Walker-Independent Features for Gait Recognition from Motion Capture Data


Aug 24, 2017
Michal Balazia, Petr Sojka

Figure 1 for Walker-Independent Features for Gait Recognition from Motion Capture Data
Figure 2 for Walker-Independent Features for Gait Recognition from Motion Capture Data
Figure 3 for Walker-Independent Features for Gait Recognition from Motion Capture Data
Figure 4 for Walker-Independent Features for Gait Recognition from Motion Capture Data
* Preprint. Full paper published at the Joint IAPR International Workshops on Structural and Syntactic Pattern Recognition and Statistical Techniques in Pattern Recognition (S+SSPR), Merida, Mexico. pp. 310--321, Springer LNCS volume 10029, Nov 2016. DOI: 10.1007/978-3-319-49055-7_28. arXiv admin note: substantial text overlap with arXiv:1609.04392 
  Access Paper or Ask Questions

Learning Robust Features for Gait Recognition by Maximum Margin Criterion


Aug 24, 2017
Michal Balazia, Petr Sojka

Figure 1 for Learning Robust Features for Gait Recognition by Maximum Margin Criterion
Figure 2 for Learning Robust Features for Gait Recognition by Maximum Margin Criterion
Figure 3 for Learning Robust Features for Gait Recognition by Maximum Margin Criterion
Figure 4 for Learning Robust Features for Gait Recognition by Maximum Margin Criterion
* Preprint. Full paper published at the 23rd IEEE/IAPR International Conference on Pattern Recognition (ICPR), Cancun, Mexico, Dec 2016. pp. 901-906 IEEE Xplore DL, March 2017. DOI: 10.1109/ICPR.2016.7899750 
  Access Paper or Ask Questions

You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data


Jul 27, 2017
Michal Balazia, Petr Sojka

Figure 1 for You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data
Figure 2 for You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data
Figure 3 for You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data
Figure 4 for You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data
* Preprint. Full paper accepted at the IEEE/IAPR International Joint Conference on Biometrics (IJCB), Denver, Colorado, USA, Oct 2017. 6 pages + 2 pages referenes 
  Access Paper or Ask Questions