This paper presents a novel method for representing actions in terms of multinomial distributions of frequent sequential patterns of different length. Frequent sequential patterns are series of data descriptors that occur many times in the data. This paper proposes to learn a codebook of frequent sequential patterns by means of an apriori-like algorithm, and to represent an action with a Bag-of-Frequent-Sequential-Patterns approach. Preliminary experiments of the proposed method have been conducted for action classification on skeletal data. The method achieves state-of-the-art accuracy value in cross-subject validation.

Monteleone, V., Lo Presti, L., La Cascia, M. (2017). Hop: Histogram of patterns for human action representation. In S. Battiato, G. Gallo, R. Schettini, F. Stanco (a cura di), Image Analysis and Processing - ICIAP 2017. Part I (pp. 457-468). Springer Verlag [10.1007/978-3-319-68560-1_41].

Hop: Histogram of patterns for human action representation

Monteleone, Vito;Lo Presti, Liliana
;
La Cascia, Marco
2017-01-01

Abstract

This paper presents a novel method for representing actions in terms of multinomial distributions of frequent sequential patterns of different length. Frequent sequential patterns are series of data descriptors that occur many times in the data. This paper proposes to learn a codebook of frequent sequential patterns by means of an apriori-like algorithm, and to represent an action with a Bag-of-Frequent-Sequential-Patterns approach. Preliminary experiments of the proposed method have been conducted for action classification on skeletal data. The method achieves state-of-the-art accuracy value in cross-subject validation.
2017
978-3-319-68559-5
Monteleone, V., Lo Presti, L., La Cascia, M. (2017). Hop: Histogram of patterns for human action representation. In S. Battiato, G. Gallo, R. Schettini, F. Stanco (a cura di), Image Analysis and Processing - ICIAP 2017. Part I (pp. 457-468). Springer Verlag [10.1007/978-3-319-68560-1_41].
File in questo prodotto:
File Dimensione Formato  
2017 ICIAPa.pdf

Solo gestori archvio

Tipologia: Versione Editoriale
Dimensione 886.06 kB
Formato Adobe PDF
886.06 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
ICIAP2017 index.pdf

Solo gestori archvio

Descrizione: indice
Tipologia: Versione Editoriale
Dimensione 296.5 kB
Formato Adobe PDF
296.5 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/279865
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact