Recognizing User-Defined Subsequences in Human Motion Data

D 2019

Recognizing User-Defined Subsequences in Human Motion Data

SEDMIDUBSKÝ, Jan a Pavel ZEZULA

Základní údaje

Originální název

Recognizing User-Defined Subsequences in Human Motion Data

Autoři

SEDMIDUBSKÝ, Jan (203 Česká republika, garant, domácí) a Pavel ZEZULA (203 Česká republika, domácí)

Vydání

New York, NY, USA, International Conference on Multimedia Retrieval (ICMR), od s. 395-398, 4 s. 2019

Nakladatel

ACM

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Kód RIV

RIV/00216224:14330/19:00107370

Organizační jednotka

Fakulta informatiky

ISBN

978-1-4503-6765-3

DOI

http://dx.doi.org/10.1145/3323873.3326922

UT WoS

000482188900058

Klíčová slova anglicky

3D skeleton sequence;action recognition;deep features;kNN

Štítky

DISA

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 15. 4. 2020 10:21, doc. RNDr. Jan Sedmidubský, Ph.D.

Anotace

V originále

Motion capture technologies digitize human movements by tracking 3D positions of specific skeleton joints in time. Such spatio-temporal multimedia data have an enormous application potential in many fields, ranging from computer animation, through security and sports to medicine, but their computerized processing is a difficult problem. In this paper, we focus on an important task of recognition of a user-defined motion, based on a collection of labelled actions known in advance. We utilize current advances in deep feature learning and scalable similarity retrieval to build an effective and efficient k-nearest-neighbor recognition technique for 3D human motion data. The properties of the technique are demonstrated by a web application which allows a user to browse long motion sequences and specify any subsequence as the input for probabilistic recognition based on 130 predefined classes.

Návaznosti

GA19-02033S, projekt VaV

Název: Vyhledávání, analytika a anotace datových toků lidských pohybů

Investor: Grantová agentura ČR, Searching, Mining, and Annotating Human Motion Streams

Citovat

SEDMIDUBSKÝ, Jan a Pavel ZEZULA. Recognizing User-Defined Subsequences in Human Motion Data. Online. In International Conference on Multimedia Retrieval (ICMR). New York, NY, USA: ACM, 2019, s. 395-398. ISBN 978-1-4503-6765-3. Dostupné z: https://dx.doi.org/10.1145/3323873.3326922.

@inproceedings{1525476,
   author = {Sedmidubský, Jan and Zezula, Pavel},
   address = {New York, NY, USA},
   booktitle = {International Conference on Multimedia Retrieval (ICMR)},
   doi = {http://dx.doi.org/10.1145/3323873.3326922},
   keywords = {3D skeleton sequence;action recognition;deep features;kNN},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {New York, NY, USA},
   isbn = {978-1-4503-6765-3},
   pages = {395-398},
   publisher = {ACM},
   title = {Recognizing User-Defined Subsequences in Human Motion Data},
   year = {2019}
}

TY  - JOUR
ID  - 1525476
AU  - Sedmidubský, Jan - Zezula, Pavel
PY  - 2019
TI  - Recognizing User-Defined Subsequences in Human Motion Data
PB  - ACM
CY  - New York, NY, USA
SN  - 9781450367653
KW  - 3D skeleton sequence;action recognition;deep features;kNN
N2  - Motion capture technologies digitize human movements by tracking 3D positions of specific skeleton joints in time. Such spatio-temporal multimedia data have an enormous application potential in many fields, ranging from computer animation, through security and sports to medicine, but their computerized processing is a difficult problem. In this paper, we focus on an important task of recognition of a user-defined motion, based on a collection of labelled actions known in advance. We utilize current advances in deep feature learning and scalable similarity retrieval to build an effective and efficient k-nearest-neighbor recognition technique for 3D human motion data. The properties of the technique are demonstrated by a web application which allows a user to browse long motion sequences and specify any subsequence as the input for probabilistic recognition based on 130 predefined classes.
ER  -

SEDMIDUBSKÝ, Jan a Pavel ZEZULA. Recognizing User-Defined Subsequences in Human Motion Data. Online. In \textit{International Conference on Multimedia Retrieval (ICMR)}. New York, NY, USA: ACM, 2019, s.~395-398. ISBN~978-1-4503-6765-3. Dostupné z: https://dx.doi.org/10.1145/3323873.3326922.

Podrobný výpis o publikaci