Probabilistic Classification of Skeleton Sequences

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F18%3A00100948" target="_blank" >RIV/00216224:14330/18:00100948 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-98812-2_4" target="_blank" >http://dx.doi.org/10.1007/978-3-319-98812-2_4</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-98812-2_4" target="_blank" >10.1007/978-3-319-98812-2_4</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Probabilistic Classification of Skeleton Sequences

Popis výsledku v původním jazyce

Automatic classification of 3D skeleton sequences of human motions has applications in many domains, ranging from entertainment to medicine. The classification is a difficult problem as the motions belonging to the same class needn't be well segmented and can be performed by subjects of various body sizes in different styles and speeds. The state-of-the-art recognition approaches commonly solve this problem by training recurrent neural networks to learn the contextual dependency in both spatial and temporal domains. In this paper, we employ a distance-based similarity measure, based on deep convolutional features, to search for the k-nearest motions with respect to a query motion being classified. The retrieved neighbors are analyzed and re-ranked by additional measures that are automatically chosen for individual queries. The combination of deep features, dynamism in the similarity-measure selection, and a new kNN classifier brings the highest classification accuracy on a challenging dataset with 130 classes. Moreover, the proposed approach can promptly react to changing training data without any need for a retraining process.

Název v anglickém jazyce

Probabilistic Classification of Skeleton Sequences

Popis výsledku anglicky

Automatic classification of 3D skeleton sequences of human motions has applications in many domains, ranging from entertainment to medicine. The classification is a difficult problem as the motions belonging to the same class needn't be well segmented and can be performed by subjects of various body sizes in different styles and speeds. The state-of-the-art recognition approaches commonly solve this problem by training recurrent neural networks to learn the contextual dependency in both spatial and temporal domains. In this paper, we employ a distance-based similarity measure, based on deep convolutional features, to search for the k-nearest motions with respect to a query motion being classified. The retrieved neighbors are analyzed and re-ranked by additional measures that are automatically chosen for individual queries. The combination of deep features, dynamism in the similarity-measure selection, and a new kNN classifier brings the highest classification accuracy on a challenging dataset with 130 classes. Moreover, the proposed approach can promptly react to changing training data without any need for a retraining process.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</a><br>

Návaznosti

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

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

29th International Conference on Database and Expert Systems Applications (DEXA 2018)

ISBN

9783319988115

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

16

Strana od-do

50-65

Název nakladatele

Springer

Místo vydání

Switzerland

Místo konání akce

Regensburg, Germany

Datum konání akce

1. 1. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000460551600004