Automatic Summarization of Activities Depicted in Instructional Videos by Use of Speech Analysis

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Existing activity recognition based assistive living solutions have adopted a relatively rigid approach to modelling activities. To address the deficiencies of such approaches, a goal-oriented solution has been proposed that will offer a method of flexibly modelling activities. This approach does, however, have a disadvantage in that the performance of goals may vary hence requiring differing video clips to be associated with these variations. In order to address this shortcoming, the use of rich metadata to facilitate automatic sequencing and matching of appropriate video clips is necessary. This paper introduces a mechanism of automatically generating rich metadata which details the actions depicted in video files to facilitate matching and sequencing. This mechanism was evaluated with 14 video files, producing annotations with a high degree of accuracy.
LanguageEnglish
Title of host publicationAmbient Assisted Living and Daily Activities
Pages123-130
Volume8868
DOIs
Publication statusPublished - 3 Dec 2014

Fingerprint

Speech analysis
Metadata

Keywords

  • Annotation
  • Automated Speech Recognition
  • Parsing
  • Ontology
  • Assistive Living
  • Smart Environments
  • Video
  • Guidance

Cite this

@inbook{38572548fbb84d09bf95a37c75ce42bf,
title = "Automatic Summarization of Activities Depicted in Instructional Videos by Use of Speech Analysis",
abstract = "Existing activity recognition based assistive living solutions have adopted a relatively rigid approach to modelling activities. To address the deficiencies of such approaches, a goal-oriented solution has been proposed that will offer a method of flexibly modelling activities. This approach does, however, have a disadvantage in that the performance of goals may vary hence requiring differing video clips to be associated with these variations. In order to address this shortcoming, the use of rich metadata to facilitate automatic sequencing and matching of appropriate video clips is necessary. This paper introduces a mechanism of automatically generating rich metadata which details the actions depicted in video files to facilitate matching and sequencing. This mechanism was evaluated with 14 video files, producing annotations with a high degree of accuracy.",
keywords = "Annotation, Automated Speech Recognition, Parsing, Ontology, Assistive Living, Smart Environments, Video, Guidance",
author = "Joseph Rafferty and Chris Nugent and J. Liu and Liming Chen",
year = "2014",
month = "12",
day = "3",
doi = "10.1007/978-3-319-13105-4_20",
language = "English",
isbn = "978-3-319-13104-7",
volume = "8868",
pages = "123--130",
booktitle = "Ambient Assisted Living and Daily Activities",

}

Automatic Summarization of Activities Depicted in Instructional Videos by Use of Speech Analysis. / Rafferty, Joseph; Nugent, Chris; Liu, J.; Chen, Liming.

Ambient Assisted Living and Daily Activities. Vol. 8868 2014. p. 123-130.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Automatic Summarization of Activities Depicted in Instructional Videos by Use of Speech Analysis

AU - Rafferty, Joseph

AU - Nugent, Chris

AU - Liu, J.

AU - Chen, Liming

PY - 2014/12/3

Y1 - 2014/12/3

N2 - Existing activity recognition based assistive living solutions have adopted a relatively rigid approach to modelling activities. To address the deficiencies of such approaches, a goal-oriented solution has been proposed that will offer a method of flexibly modelling activities. This approach does, however, have a disadvantage in that the performance of goals may vary hence requiring differing video clips to be associated with these variations. In order to address this shortcoming, the use of rich metadata to facilitate automatic sequencing and matching of appropriate video clips is necessary. This paper introduces a mechanism of automatically generating rich metadata which details the actions depicted in video files to facilitate matching and sequencing. This mechanism was evaluated with 14 video files, producing annotations with a high degree of accuracy.

AB - Existing activity recognition based assistive living solutions have adopted a relatively rigid approach to modelling activities. To address the deficiencies of such approaches, a goal-oriented solution has been proposed that will offer a method of flexibly modelling activities. This approach does, however, have a disadvantage in that the performance of goals may vary hence requiring differing video clips to be associated with these variations. In order to address this shortcoming, the use of rich metadata to facilitate automatic sequencing and matching of appropriate video clips is necessary. This paper introduces a mechanism of automatically generating rich metadata which details the actions depicted in video files to facilitate matching and sequencing. This mechanism was evaluated with 14 video files, producing annotations with a high degree of accuracy.

KW - Annotation

KW - Automated Speech Recognition

KW - Parsing

KW - Ontology

KW - Assistive Living

KW - Smart Environments

KW - Video

KW - Guidance

U2 - 10.1007/978-3-319-13105-4_20

DO - 10.1007/978-3-319-13105-4_20

M3 - Chapter

SN - 978-3-319-13104-7

VL - 8868

SP - 123

EP - 130

BT - Ambient Assisted Living and Daily Activities

ER -