SegmentCodeList: Unsupervised Representation Learning for Human Skeleton Data Retrieval

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F23%3A00130177" target="_blank" >RIV/00216224:14330/23:00130177 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-031-28238-6_8" target="_blank" >http://dx.doi.org/10.1007/978-3-031-28238-6_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-28238-6_8" target="_blank" >10.1007/978-3-031-28238-6_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SegmentCodeList: Unsupervised Representation Learning for Human Skeleton Data Retrieval

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

SegmentCodeList: Unsupervised Representation Learning for Human Skeleton Data Retrieval

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

<a href="/cs/project/EF16_019%2F0000822" target="_blank" >EF16_019/0000822: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

45th European Conference on Information Retrieval (ECIR)

ISBN

9783031282379

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

15

Strana od-do

110-124

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Dublin, Ireland

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000995489700008