Understanding the Gap between 2D and 3D Skeleton-Based Action Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F19%3A00107709" target="_blank" >RIV/00216224:14330/19:00107709 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ISM46123.2019.00041" target="_blank" >http://dx.doi.org/10.1109/ISM46123.2019.00041</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ISM46123.2019.00041" target="_blank" >10.1109/ISM46123.2019.00041</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Understanding the Gap between 2D and 3D Skeleton-Based Action Recognition

Popis výsledku v původním jazyce

Large volumes of RGB video data are recorded and processed every day. One of the embedded data modality within these videos is the information about human motions. Up to now, this information has been almost unfeasible to extract, and thus human-motion understanding research has been mainly limited to 3D skeleton data captured by dedicated hardware only. However, with recent advances in computer vision, it is possible to estimate 2D skeleton sequences from ordinary videos quite accurately. Such 2D skeleton data possess an excellent potential for future motion understanding applications. In this paper, we adopt a state-of-the-art bidirectional LSTM network to analyze the accuracy gap in the expressive power of 2D and 3D skeleton data recorded simultaneously on a high number of 20k human actions. We further examine how the missing depth information and fluctuations in 2D skeleton sizes influence the recognition rate. We also demonstrate the suitability of 2D skeleton data for general daily activity recognition by reporting baselines on the PKU-MMD dataset.

Název v anglickém jazyce

Understanding the Gap between 2D and 3D Skeleton-Based Action Recognition

Popis výsledku anglicky

Large volumes of RGB video data are recorded and processed every day. One of the embedded data modality within these videos is the information about human motions. Up to now, this information has been almost unfeasible to extract, and thus human-motion understanding research has been mainly limited to 3D skeleton data captured by dedicated hardware only. However, with recent advances in computer vision, it is possible to estimate 2D skeleton sequences from ordinary videos quite accurately. Such 2D skeleton data possess an excellent potential for future motion understanding applications. In this paper, we adopt a state-of-the-art bidirectional LSTM network to analyze the accuracy gap in the expressive power of 2D and 3D skeleton data recorded simultaneously on a high number of 20k human actions. We further examine how the missing depth information and fluctuations in 2D skeleton sizes influence the recognition rate. We also demonstrate the suitability of 2D skeleton data for general daily activity recognition by reporting baselines on the PKU-MMD dataset.

Druh

D - Stať ve sborníku

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

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

21st IEEE International Symposium on Multimedia (ISM)

ISBN

9781728156064

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

192-195

Název nakladatele

IEEE Computer Society

Místo vydání

Neuveden

Místo konání akce

San Diego, California, USA

Datum konání akce

1. 1. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000528909200030