Faculty staff

Curriculum Vitae

Person-Related Identification Information

• doc. RNDr. Jan Sedmidubský, Ph.D., born: October 30, 1982, in Mostiště, married, 2 children

Department

• Department of Machine Learning and Data Processing
  Faculty of Informatics
  Masaryk University
  Botanická 554/68a
  602 00 Brno

Employment - Position

• Scientific researcher

Education and Academic Qualifications

• 2021: habilitation at Faculty of Informatics, Masaryk University (FI MU), Brno, Czech Republic
• 2006–2011: Ph.D. (doctoral degree programme "Informatics"); FI MU
• 2008: RNDr. (advanced master's state examination in "Informatics"); FI MU
• 2004–2006: Mgr. (master's degree programme "Applied Informatics"); FI MU
• 2001–2004: Bc. (bachelor's degree programme "Applied Informatics"); FI MU

Employment

• 7/2015–present: Scientific researcher (FI MU)
• 2009–6/2015: Research and development worker (FI MU)
• 2007–2009: Teacher of visually impaired, deaf, and hearing impaired students (Teiresias Centre, Masaryk University)

Teaching Activities

• 2017–present: teaching the "Advanced Search Techniques for Large Scale Data Analytics" (PA212) course (FI MU)
• 2006–present: teaching the "Database Systems" (PB154) class exercises (FI MU)
• 2007–2009: teaching the "Database Systems" (PB154) lectures and class exercises for visually impaired, deaf, and hearing impaired students (Teiresias Centre, Masaryk University)
• 2011–present: consultant of 4 doctoral students (three of them already defended their dissertation theses - all evaluated as excellent)
• 2007–present: leading bachelor's and master's theses (four of them were awarded)

Scientific and Research Activities

• Areas of interest:
  AI, similarity search, content-based processing of multimedia and motion capture data, deep neural networks, databases
  
  Cooperation on scholarly and development projects; selected projects:
• 2023–2025: "VisioTherapy: Supporting physiotherapy treatments using computer-based movement analysis" (FW09020055); Technology Agency of the Czech Republic (TAČR) – co-principal investigator
• 2023–2026: "Automated digital data forensics lab for complex crime detection" (VK01010147); Ministry of the Interior of the CR
• 2021–2023: "Diagnosis of Dyslexia using Eye-Tracking and Artificial Intelligence" (TL05000177); Technology Agency of the Czech Republic (TAČR)
• 2020–2022: "Improving Treatments in Cerebral-Palsy Children using Artificial Intelligence" (MUNI/G/1585/2019); Grant Agency of Masaryk University (Interdisciplinary projects)
• 2019–2021: "Searching, Mining, and Annotating Human Motion Streams" (GA19-02033S); Czech Science Foundation (GAČR)
• 2012–2018: "Center of Excellence on Multi-modal Data Interpretation on a Very Large Scale" (GBP103/12/G084); Czech Science Foundation (GAČR)
• 2012–2015: "Efficient Searching in Large Biometric Data" (VG20122015073); Ministry of the Interior of the CR (Security Research for the Needs of the State 2010–2015)
• 2010–2012: "Content-based Image Retrieval on the Web Scale" (GAP103/10/0886); Czech Science Foundation (GAČR)
• 2009–2011: "Similarity Searching in Very Large Multimedia Databases" (GA201/09/0683); Czech Science Foundation (GAČR)
• 2006–2009: "Search on Audio-visual content using Peer-to-peer Information Retrieval" (SAPIR; 045128); European Union – 6th Specific RTD Programme

Internship

• 3/2023: one-month research stay at ISTI-CNR (Pisa, Italy)
• 5–6/2022: one-month research stay at ISTI-CNR (Pisa, Italy)

University Activities

• 2013–present: committee member of state examination boards

Activities Outside University

• 2022–2024: Program committee member of the International Conference on Similarity Search and Applications (SISAP)
• 2024: Program committee member of the 22nd Cognition and Artificial Life (CAL) conference

Awards Related to Science and Research

• 2023: MUNI Scientist Award
• 2023: co-author of publication "Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language" awarded as "Best Short Paper Award Honorable Mention" at the A* 46th International Conference on Research and Development in Information Retrieval (SIGIR), Taiwan
• 2017: co-author of publication "A Real-Time Annotation of Motion Data Streams" awarded as the best student paper at the 19th International Symposium on Multimedia, Taiwan
• 2016: co-author of publication "Building a Web-scale Image Similarity Search System" evaluated as excellent within the Czech publication evaluation programme "Pilíř II"
• 2011: Rector's award at Masaryk University for distinguished dissertation thesis "Self-organizing Similarity Search: The Social Network Approach"
• 2011: Dean's award at FI MU for distinguished dissertation thesis "Self-organizing Similarity Search: The Social Network Approach"
• 2009: award for the third best presentation of the year at Seminar of Informatics at FI MU
• 2008: member of the team which was awarded the prestigious IBM Shared University Research Award for the "Web-scale Similarity Search in Multimedia Data" project

Major Publications

• ČERNEK, Andrej, Jan SEDMIDUBSKÝ a Petra BUDÍKOVÁ. REHAB24-6: Physical Therapy Dataset for Analyzing Pose Estimation Methods. Online. In 17th International Conference on Similarity Search and Applications (SISAP). Cham: Springer, 2024, s. 18-33. ISBN 978-3-031-75822-5. Dostupné z: https://dx.doi.org/10.1007/978-3-031-75823-2_2. URL Collected dataset (REHAB24-6: A multi-modal dataset of physical rehabilitation exercises) info
• JÁNOŠOVÁ, Miriama, Petra BUDÍKOVÁ a Jan SEDMIDUBSKÝ. Personalized Similarity Models for Evaluating Rehabilitation Exercises from Monocular Videos. Online. In 17th International Conference on Similarity Search and Applications (SISAP). Cham: Springer, 2024, s. 73-87. ISBN 978-3-031-75822-5. Dostupné z: https://dx.doi.org/10.1007/978-3-031-75823-2_7. URL info
• SEDMIDUBSKÝ, Jan, Nicol DOSTÁLOVÁ, Roman ŠVAŘÍČEK a Wolf CULEMANN. ETDD70: Eye-Tracking Dataset for Classification of Dyslexia using AI-based Methods. Online. In 17th International Conference on Similarity Search and Applications (SISAP). Cham: Springer, 2024, s. 34-48. ISBN 978-3-031-75822-5. Dostupné z: https://dx.doi.org/10.1007/978-3-031-75823-2_3. URL Collected dataset (ETDD70: Eye-tracking dyslexia dataset) info
• SEDMIDUBSKÝ, Jan, Fabio CARRARA a Giuseppe AMATO. SegmentCodeList: Unsupervised Representation Learning for Human Skeleton Data Retrieval. Online. In 45th European Conference on Information Retrieval (ECIR). Cham: Springer, 2023, s. 110-124. ISBN 978-3-031-28237-9. Dostupné z: https://dx.doi.org/10.1007/978-3-031-28238-6_8. info
• MESSINA, Nicola, Jan SEDMIDUBSKÝ, Falchi FABRIZIO a Tomáš REBOK. Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language. Online. In 46th International Conference on Research and Development in Information Retrieval (SIGIR). New York, NY, USA: Association for Computing Machinery, 2023, s. 2420-2425. ISBN 978-1-4503-9408-6. Dostupné z: https://dx.doi.org/10.1145/3539618.3592069. URL info
• MÍČ, Vladimír, Jan SEDMIDUBSKÝ a Pavel ZEZULA. CRANBERRY: Memory-Effective Search in 100M High-Dimensional CLIP Vectors. Online. In Oscar Pedreira, Vladimir Estivill-Castro. 16th International Conference on Similarity Search and Applications (SISAP). Cham: Springer, 2023, s. 300-308. ISBN 978-3-031-46993-0. Dostupné z: https://dx.doi.org/10.1007/978-3-031-46994-7_26. URL info
• ELIÁŠ, Petr, Matúš MACKO, Jan SEDMIDUBSKÝ a Pavel ZEZULA. Tracking subjects and detecting relationships in crowded city videos. Multimedia Tools and Applications. Springer, 2022, Neuveden, January, s. 1-23. ISSN 1380-7501. Dostupné z: https://dx.doi.org/10.1007/s11042-021-11891-z. URL info
• SEDMIDUBSKÝ, Jan, Tomáš LJUTENKO a Pavel ZEZULA. GaitQualityAnalyzer. 2022. URL info
• ELIÁŠ, Petr, Jan SEDMIDUBSKÝ a Pavel ZEZULA. Understanding the Limits of 2D Skeletons for Action Recognition. Multimedia Systems. 2021, roč. 27, č. 3, s. 547-561. ISSN 0942-4962. Dostupné z: https://dx.doi.org/10.1007/s00530-021-00754-0. URL info
• SEDMIDUBSKÝ, Jan a Pavel ZEZULA. Efficient Combination of Classifiers for 3D Action Recognition. Multimedia Systems. Springer, 2021, roč. 27, č. 5, s. 941-952. ISSN 0942-4962. Dostupné z: https://dx.doi.org/10.1007/s00530-021-00767-9. URL info
• BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ, Ján HORVÁTH a Pavel ZEZULA. Efficient Retrieval of Human Motion Episodes Based on Indexed Motion-Word Representations. International Journal of Semantic Computing. World Scientific Publishing, 2021, roč. 15, č. 2, s. 189-213. ISSN 1793-351X. Dostupné z: https://dx.doi.org/10.1142/S1793351X21400031. URL info
• BUDÍKOVÁ, Petra, Jan SEDMIDUBSKÝ a Pavel ZEZULA. Efficient Indexing of 3D Human Motions. Online. In ACM International Conference on Multimedia Retrieval (ICMR). Neuveden: ACM, 2021, s. 10-18. ISBN 978-1-4503-8463-6. Dostupné z: https://dx.doi.org/10.1145/3460426.3463646. URL info
• SEDMIDUBSKÝ, Jan, Petr ELIÁŠ, Petra BUDÍKOVÁ a Pavel ZEZULA. Content-Based Management of Human Motion Data: Survey and Challenges. IEEE Access. IEEE Xplore Digital Library, 2021, roč. 9, 26 April 2021, s. 64241-64255. ISSN 2169-3536. Dostupné z: https://dx.doi.org/10.1109/ACCESS.2021.3075766. URL info
• SEDMIDUBSKÝ, Jan, Petra BUDÍKOVÁ, Vlastislav DOHNAL a Pavel ZEZULA. Motion Words: A Text-like Representation of 3D Skeleton Sequences. Online. In 42nd European Conference on Information Retrieval (ECIR). Cham: Springer, 2020, s. 527-541. ISBN 978-3-030-45438-8. Dostupné z: https://dx.doi.org/10.1007/978-3-030-45439-5_35. info
• SEDMIDUBSKÝ, Jan, Petr ELIÁŠ a Pavel ZEZULA. Searching for Variable-Speed Motions in Long Sequences of Motion Capture Data. Information Systems. 2019, roč. 80, February, s. 148-158. ISSN 0306-4379. Dostupné z: https://dx.doi.org/10.1016/j.is.2018.04.002. URL info
• SEDMIDUBSKÝ, Jan, Petr ELIÁŠ a Pavel ZEZULA. Benchmarking Search and Annotation in Continuous Human Skeleton Sequences. Online. In International Conference on Multimedia Retrieval (ICMR). New York, NY, USA: ACM, 2019, s. 38-42. ISBN 978-1-4503-6765-3. Dostupné z: https://dx.doi.org/10.1145/3323873.3325013. info
• CARRARA, Fabio, Petr ELIÁŠ, Jan SEDMIDUBSKÝ a Pavel ZEZULA. LSTM-Based Real-Time Action Detection and Prediction in Human Motion Streams. Multimedia Tools and Applications. Springer US, 2019, roč. 78, č. 19, s. 27309-27331. ISSN 1380-7501. Dostupné z: https://dx.doi.org/10.1007/s11042-019-07827-3. URL info
• SEDMIDUBSKÝ, Jan, Petr ELIÁŠ a Pavel ZEZULA. Effective and Efficient Similarity Searching in Motion Capture Data. Multimedia Tools and Applications. Springer US, 2018, roč. 77, č. 10, s. 12073-12094. ISSN 1380-7501. Dostupné z: https://dx.doi.org/10.1007/s11042-017-4859-7. info
• SVEC, Jan, Josef V. PSUTKA, Jan TRMAL, Lubos SMIDL, Pavel IRCING a Jan SEDMIDUBSKÝ. ON THE USE OF GRAPHEME MODELS FOR SEARCHING IN LARGE SPOKEN ARCHIVES. In 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018). Neuveden: IEEE Computer Society, 2018, s. 6259-6263. ISBN 978-1-5386-4658-8. Dostupné z: https://dx.doi.org/10.1109/ICASSP.2018.8461774. info
• SEDMIDUBSKÝ, Jan a Pavel ZEZULA. Probabilistic Classification of Skeleton Sequences. In S. Hartmann et al. 29th International Conference on Database and Expert Systems Applications (DEXA 2018). Switzerland: Springer, 2018, s. 50-65. ISBN 978-3-319-98811-5. Dostupné z: https://dx.doi.org/10.1007/978-3-319-98812-2_4. info
• SEDMIDUBSKÝ, Jan a Pavel ZEZULA. Similarity-Based Processing of Motion Capture Data. Online. In Proceedings of the ACM Conference on Multimedia (MM 2018). New York, NY, USA: ACM, 2018, s. 2087-2089. ISBN 978-1-4503-5665-7. Dostupné z: https://dx.doi.org/10.1145/3240508.3241468. info
• SEDMIDUBSKÝ, Jan, Pavel ZEZULA a Jan ŠVEC. Fast Subsequence Matching in Motion Capture Data. In 21st European Conference on Advances in Databases and Information Systems. Cham: Springer, 2017, s. 59-72. ISBN 978-3-319-66916-8. Dostupné z: https://dx.doi.org/10.1007/978-3-319-66917-5_5. info
• ELIÁŠ, Petr, Jan SEDMIDUBSKÝ a Pavel ZEZULA. A Real-Time Annotation of Motion Data Streams. In 19th IEEE International Symposium on Multimedia. Neuveden: IEEE Computer Society, 2017, s. 154-161. ISBN 978-1-5386-2937-6. Dostupné z: https://dx.doi.org/10.1109/ISM.2017.29. info
• VALČÍK, Jakub, Jan SEDMIDUBSKÝ a Pavel ZEZULA. Assessing similarity models for human-motion retrieval applications. Computer Animation and Virtual Worlds. John Wiley & Sons Ltd, 2016, roč. 27, č. 5, s. 484-500. ISSN 1546-4261. Dostupné z: https://dx.doi.org/10.1002/cav.1674. info
• SEDMIDUBSKÝ, Jan, Petr ELIÁŠ a Pavel ZEZULA. Similarity Searching in Long Sequences of Motion Capture Data. In L. Amsaleg et al. Proceedings of 9th International Conference on Similarity Search and Applications (SISAP 2016), LNCS 9939. Cham (ZG): Springer International Publishing AG, 2016, s. 271-285. ISBN 978-3-319-46758-0. Dostupné z: https://dx.doi.org/10.1007/978-3-319-46759-7_21. info
• VALČÍK, Jakub, Jan SEDMIDUBSKÝ a Pavel ZEZULA. Improving Kinect-Skeleton Estimation. In S. Battiato et al. Advanced Concepts for Intelligent Vision Systems (ACIVS 2015), LNCS 9386. Switzerland: Springer, 2015, s. 575-587. ISBN 978-3-319-25902-4. Dostupné z: https://dx.doi.org/10.1007/978-3-319-25903-1_50. info
• SEDMIDUBSKÝ, Jan, Jakub VALČÍK a Pavel ZEZULA. Multi-modal Person Identification. 2015. URL info
• SEDMIDUBSKÝ, Jan, Michal BATKO a Pavel ZEZULA. Face-based People Searching in Videos. In P. Serdyukov et al. 35th European Conference on Information Retrieval (ECIR 2013), LNCS 7814. Berlin Heidelberg: Springer-Verlag, 2013, s. 853-856. ISBN 978-3-642-36972-8. Dostupné z: https://dx.doi.org/10.1007/978-3-642-36973-5_101. info
• SEDMIDUBSKÝ, Jan, Jakub VALČÍK a Pavel ZEZULA. A Key-Pose Similarity Algorithm for Motion Data Retrieval. In J. Blanc-Talon et al. (Eds.). Proceedings of 12th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2013), LNCS 8192. Switzerland: Springer International Publishing, 2013, s. 669-681. ISBN 978-3-319-02894-1. Dostupné z: https://dx.doi.org/10.1007/978-3-319-02895-8_60. info
• BATKO, Michal, Fabrizio FALCHI, Claudio LUCCHESE, David NOVÁK, Raffaele PEREGO, Fausto RABITTI, Jan SEDMIDUBSKÝ a Pavel ZEZULA. Building a Web-scale Image Similarity Search System. Multimedia Tools and Applications. Springer Netherlands, 2010, roč. 47, č. 3, s. 599-629. ISSN 1380-7501. URL info
• BATKO, Michal, Vlastislav DOHNAL, David NOVÁK a Jan SEDMIDUBSKÝ. MUFIN: A Multi-Feature Indexing Network. In 2nd International Workshop on Similarity Search and Applications. Los Alamitos, CA 90720-1314: IEEE Computer Society, 2009, s. 158-159. ISBN 978-0-7695-3765-8. info
• SEDMIDUBSKÝ, Jan, Stanislav BARTOŇ, Vlastislav DOHNAL a Pavel ZEZULA. Adaptive Approximate Similarity Searching through Metric Social Networks. In 24th International Conference on Data Engineering (ICDE 2008). Los Alamitos CA: IEEE Computer Society, 2008, s. 1424-1426. ISBN 978-1-4244-1836-7. URL info

2024/05/18