SEDMIDUBSKÝ, Jan, Fabio CARRARA and Giuseppe AMATO. SegmentCodeList: Unsupervised Representation Learning for Human Skeleton Data Retrieval. Online. In 45th European Conference on Information Retrieval (ECIR). Cham: Springer, 2023, p. 110-124. ISBN 978-3-031-28237-9. Available from: https://dx.doi.org/10.1007/978-3-031-28238-6_8.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name SegmentCodeList: Unsupervised Representation Learning for Human Skeleton Data Retrieval
Authors SEDMIDUBSKÝ, Jan (203 Czech Republic, guarantor, belonging to the institution), Fabio CARRARA and Giuseppe AMATO.
Edition Cham, 45th European Conference on Information Retrieval (ECIR), p. 110-124, 15 pp. 2023.
Publisher Springer
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10200 1.2 Computer and information sciences
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
Impact factor Impact factor: 0.402 in 2005
RIV identification code RIV/00216224:14330/23:00130177
Organization unit Faculty of Informatics
ISBN 978-3-031-28237-9
ISSN 0302-9743
Doi http://dx.doi.org/10.1007/978-3-031-28238-6_8
UT WoS 000995489700008
Keywords in English 3D skeleton sequence;segment similarity;unsupervised feature learning;Variational AutoEncoder;segment code list;action retrieval
Tags DISA
Tags International impact, Reviewed
Changed by Changed by: RNDr. Pavel Šmerk, Ph.D., učo 3880. Changed: 7/4/2024 22:39.
Abstract
Recent progress in pose-estimation methods enables the extraction of sufficiently-precise 3D human skeleton data from ordinary videos, which offers great opportunities for a wide range of applications. However, such spatio-temporal data are typically extracted in the form of a continuous skeleton sequence without any information about semantic segmentation or annotation. To make the extracted data reusable for further processing, there is a need to access them based on their content. In this paper, we introduce a universal retrieval approach that compares any two skeleton sequences based on temporal order and similarities of their underlying segments. The similarity of segments is determined by their content-preserving low-dimensional code representation that is learned using the Variational AutoEncoder principle in an unsupervised way. The quality of the proposed representation is validated in retrieval and classification scenarios; our proposal outperforms the state-of-the-art approaches in effectiveness and reaches speed-ups up to 64x on common skeleton sequence datasets.
Links
EF16_019/0000822, research and development projectName: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur
PrintDisplayed: 27/4/2024 08:37