Efficient Retrieval of Human Motion Episodes Based on Indexed Motion-Word Representations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F21%3A00118932" target="_blank" >RIV/00216224:14330/21:00118932 - isvavai.cz</a>

Výsledek na webu

<a href="https://dx.doi.org/10.1142/S1793351X21400031" target="_blank" >https://dx.doi.org/10.1142/S1793351X21400031</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1142/S1793351X21400031" target="_blank" >10.1142/S1793351X21400031</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Retrieval of Human Motion Episodes Based on Indexed Motion-Word Representations

Popis výsledku v původním jazyce

With the increasing availability of human motion data captured in the form of 2D or 3D skeleton sequences, more complex motion recordings need to be processed. In this paper, we focus on similarity-based indexing and efficient retrieval of motion episodes - medium-sized skeleton sequences that consist of multiple semantic actions and correspond to some logical motion unit (e.g., a figure skating performance). As a first step towards efficient retrieval, we apply the motion-word technique to transform spatio-temporal skeleton sequences into compact text-like documents. Based on these documents, we introduce a two-phase retrieval scheme that first finds a set of candidate query results and then re-ranks these candidates with more expensive application-specific methods. We further index the motion-word documents using inverted files, which allows us to retrieve the candidate documents in an efficient and scalable manner. We also propose additional query-reduction techniques that accelerate both the retrieval phases by removing semantically irrelevant parts of the motion query. Experimental evaluation is used to analyze the effects of the individual proposed techniques of the retrieval efficiency and effectiveness.

Název v anglickém jazyce

Efficient Retrieval of Human Motion Episodes Based on Indexed Motion-Word Representations

Popis výsledku anglicky

With the increasing availability of human motion data captured in the form of 2D or 3D skeleton sequences, more complex motion recordings need to be processed. In this paper, we focus on similarity-based indexing and efficient retrieval of motion episodes - medium-sized skeleton sequences that consist of multiple semantic actions and correspond to some logical motion unit (e.g., a figure skating performance). As a first step towards efficient retrieval, we apply the motion-word technique to transform spatio-temporal skeleton sequences into compact text-like documents. Based on these documents, we introduce a two-phase retrieval scheme that first finds a set of candidate query results and then re-ranks these candidates with more expensive application-specific methods. We further index the motion-word documents using inverted files, which allows us to retrieve the candidate documents in an efficient and scalable manner. We also propose additional query-reduction techniques that accelerate both the retrieval phases by removing semantically irrelevant parts of the motion query. Experimental evaluation is used to analyze the effects of the individual proposed techniques of the retrieval efficiency and effectiveness.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

<a href="/cs/project/GA19-02033S" target="_blank" >GA19-02033S: Vyhledávání, analytika a anotace datových toků lidských pohybů</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název periodika

International Journal of Semantic Computing

ISSN

1793-351X

e-ISSN

1793-7108

Svazek periodika

15

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

SG - Singapurská republika

Počet stran výsledku

25

Strana od-do

189-213

Kód UT WoS článku

000670288200004

EID výsledku v databázi Scopus

2-s2.0-85109478306