prikaz prve stranice dokumenta Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS
  Download
PDF 935.05 KB
Scientific paper - Original scientific paper
Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS
In: 2018 7th European Workshop on Visual Information Processing (EUVIP). IEEE, 2019. pp. 1-6. https://doi.org/10.1109/EUVIP.2018.8611642
Ivašić-Kos, Marina; Pobar, Miran

Cite this document

Ivašić Kos, M. & Pobar, M. (2019). Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS. 2018 7th European Workshop on Visual Information Processing (EUVIP) (pp. 1-6). IEEE. doi: 10.1109/EUVIP.2018.8611642

Ivašić Kos, Marina and Miran Pobar. "Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS." 2018 7th European Workshop on Visual Information Processing (EUVIP), IEEE, 2019, pp. 1-6. https://urn.nsk.hr/urn:nbn:hr:195:898413

Ivašić Kos, Marina and Miran Pobar. "Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS." In 2018 7th European Workshop on Visual Information Processing (EUVIP), 1-6. IEEE, 2019. Accessed 2024 November 20. https://urn.nsk.hr/urn:nbn:hr:195:898413

Ivašić Kos, M. and Pobar, M. (2019) 'Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS', 2018 7th European Workshop on Visual Information Processing (EUVIP), IEEE, pp. 1-6. Available at: https://urn.nsk.hr/urn:nbn:hr:195:898413 (Accessed 20 November 2024)

Ivašić Kos M, Pobar M. Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS. 2018 7th European Workshop on Visual Information Processing (EUVIP). IEEE; 2019. Pp. 1-6. [cited 2024 November 20] Available at: https://urn.nsk.hr/urn:nbn:hr:195:898413

M. Ivašić Kos and M. Pobar, "Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS", 2018 7th European Workshop on Visual Information Processing (EUVIP) IEEE, 2019. [Online] Available at: https://urn.nsk.hr/urn:nbn:hr:195:898413 [Accessed: 20 November 2024]

Please login to the repository to save this object to your list.
Metadata
Title (english)Building a labeled dataset for recognition of handball actions using mask R-CNN and STIPS
AuthorMarina Ivašić-Kos https://orcid.org/0000-0002-1940-5089
AuthorMiran Pobar https://orcid.org/0000-0001-5604-2128
Author's institutionUniversity of Rijeka
(Faculty of Informatics and Digital Technologies)
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract (english)
Building successful machine learning models depends on large amounts of training data that often needs to be labelled manually. We propose a method to efficiently build an action recognition dataset in the handball domain, focusing on minimizing the manual labor required to label the individual players performing the chosen actions. The method uses existing deep learning object recognition methods for player detection and combines the obtained location information with a player activity measure based on spatio-temporal interest points to track players that are performing the currently relevant action, here called active players. The method was successfully used on a challenging dataset of real-world handball practice videos, where the leading active player was correctly tracked and labeled in 84 % of cases.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionAccepted version
Publication title2018 7th European Workshop on Visual Information Processing (EUVIP)
Numberingpp. 1-6
ISBN978-1-5386-6897-9 (Electronic ISBN)
ISBN978-1-5386-6898-6 (Print on Demand(PoD) ISBN)
e-ISSN2471-8963
DOIhttps://doi.org/10.1109/EUVIP.2018.8611642
URN:NBNurn:nbn:hr:195:898413
Publication2019-01-17
ProjectNumber: IP-2016-06-8345
Title (croatian): Automatsko raspoznavanje akcija i aktivnosti u multimedijalnom sadržaju iz domene sporta
Title (english): Automatic recognition of actions and activities in multimedia content from sports domain
Acronym: RAASS
Leader: Marina Ivašić Kos
Jurisdiction: Croatia
Funding stream: IP
ConferenceTitle: 2018 7th European Workshop on Visual Information Processing (EUVIP)
Acronym: EUVIP
Location: Tampere, Finland
Start date: 2018-11-26
End date: 2018-11-28
Assembly type: Lecture
Document URLhttps://ieeexplore.ieee.org/document/8611642
Type of resourceText
PublisherIEEE
Access conditionsOpen access
Terms of useLicence In copyright icon
Public note© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Created on2023-02-12 19:44:39