Exploiting the deep learning paradigm for recognizing human actions

Pasquale Foggia*, Alessia Saggese, Nicola Strisciuglio, Mario Vento

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

28 Citations (Scopus)

Abstract

In this paper we propose a novel method for recognizing human actions by exploiting a multi-layer representation based on a deep learning based architecture. A first level feature vector is extracted and then a high level representation is obtained by taking advantage of a Deep Belief Network trained using a Restricted Boltzmann Machine. The classification is finally performed by a feed-forward neural network. The main advantage behind the proposed approach lies in the fact that the high level representation is automatically built by the system exploiting the regularities in the dataset; given a suitably large dataset, it can be expected that such a representation can outperform a hand-design description scheme. The proposed approach has been tested on two standard datasets and the achieved results, compared with state of the art algorithms, confirm its effectiveness.

Original languageEnglish
Title of host publication11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages93-98
Number of pages6
ISBN (Electronic)978-1-4799-4871-0
ISBN (Print)978-1-4799-4870-3
DOIs
Publication statusPublished - 8 Oct 2014
Externally publishedYes
Event11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014 - Seoul, Korea, Republic of
Duration: 26 Aug 201429 Aug 2014
Conference number: 11

Conference

Conference11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014
Abbreviated titleAVSS
CountryKorea, Republic of
CitySeoul
Period26/08/1429/08/14

Fingerprint Dive into the research topics of 'Exploiting the deep learning paradigm for recognizing human actions'. Together they form a unique fingerprint.

Cite this