Probabilistic Classification of Skeleton Sequences

D 2018

Probabilistic Classification of Skeleton Sequences

SEDMIDUBSKÝ, Jan a Pavel ZEZULA

Základní údaje

Originální název

Probabilistic Classification of Skeleton Sequences

Autoři

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

Vydání

Switzerland, 29th International Conference on Database and Expert Systems Applications (DEXA 2018), od s. 50-65, 16 s. 2018

Nakladatel

Springer

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

paměťový nosič (CD, DVD, flash disk)

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/18:00100948

Organizační jednotka

Fakulta informatiky

ISBN

978-3-319-98811-5

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-98812-2_4

UT WoS

000460551600004

Klíčová slova anglicky

motion capture data; nearest-neighbor search; action recognition; action classification; re-ranking; similarity measure

Štítky

core_B, DISA, firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 30. 4. 2019 08:16, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

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.

Návaznosti

GBP103/12/G084, projekt VaV

Název: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Grantová agentura ČR, Centrum pro multi-modální interpretaci dat velkého rozsahu

Citovat

SEDMIDUBSKÝ, Jan a Pavel ZEZULA. Probabilistic Classification of Skeleton Sequences. In S. Hartmann et al. 29th International Conference on Database and Expert Systems Applications (DEXA 2018). Switzerland: Springer, 2018, s. 50-65. ISBN 978-3-319-98811-5. Dostupné z: https://dx.doi.org/10.1007/978-3-319-98812-2_4.

@inproceedings{1417925,
   author = {Sedmidubský, Jan and Zezula, Pavel},
   address = {Switzerland},
   booktitle = {29th International Conference on Database and Expert Systems Applications (DEXA 2018)},
   doi = {http://dx.doi.org/10.1007/978-3-319-98812-2_4},
   editor = {S. Hartmann et al.},
   keywords = {motion capture data; nearest-neighbor search; action recognition; action classification; re-ranking; similarity measure},
   howpublished = {paměťový nosič},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-319-98811-5},
   pages = {50-65},
   publisher = {Springer},
   title = {Probabilistic Classification of Skeleton Sequences},
   year = {2018}
}

TY  - JOUR
ID  - 1417925
AU  - Sedmidubský, Jan - Zezula, Pavel
PY  - 2018
TI  - Probabilistic Classification of Skeleton Sequences
PB  - Springer
CY  - Switzerland
SN  - 9783319988115
KW  - motion capture data
KW  - nearest-neighbor search
KW  - action recognition
KW  - action classification
KW  - re-ranking
KW  - similarity measure
N2  - 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.
ER  -

SEDMIDUBSKÝ, Jan a Pavel ZEZULA. Probabilistic Classification of Skeleton Sequences. In S. Hartmann et al. \textit{29th International Conference on Database and Expert Systems Applications (DEXA 2018)}. Switzerland: Springer, 2018, s.~50-65. ISBN~978-3-319-98811-5. Dostupné z: https://dx.doi.org/10.1007/978-3-319-98812-2\_{}4.

Podrobný výpis o publikaci