Selective keyframe summarisation for egocentric videos based on semantic concept search

Paria Yousefi; Ludmila Kuncheva

Selective keyframe summarisation for egocentric videos based on semantic concept search

Paria Yousefi
, Ludmila Kuncheva

Ysgol Cyfrifiadureg a Pheirianneg

Allbwn ymchwil: Cyfraniad at gynhadledd › Papur › adolygiad gan gymheiriaid

266 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

Large volumes of egocentric video data are being continually collected every day. While the standard video summarisation approach offers all-purpose summaries, here we propose a method for selective video summarisation. The user can query the video with an unlimited vocabulary of terms. The result is a time-tagged summary of keyframes related to the query concept. Our method uses a pre-trained Convolutional Neural Network (CNN) for the semantic search, and visualises the generated summary as a compass. Two commonly used datasets were chosen for the evaluation: UTEgo egocentric video and EDUB lifelog.

Iaith wreiddiol	Saesneg
Nifer y tudalennau	6
Statws	Cyhoeddwyd - 2018
Digwyddiad	The International Image Processing Applications and Systems Conference - Sophia Antipolis, Ffrainc Hyd: 12 Rhag 2018 → 14 Rhag 2018

Cynhadledd

Cynhadledd	The International Image Processing Applications and Systems Conference
Teitl cryno	IPAS
Gwlad/Tiriogaeth	Ffrainc
Dinas	Sophia Antipolis
Cyfnod	12/12/18 → 14/12/18

Mynediad at Ddogfen

SelectiveVideoSummarisationProflen, 1.54 MB

Dyfynnu hyn

@conference{2ef47574e52a4e02839583188fe7ef30,

title = "Selective keyframe summarisation for egocentric videos based on semantic concept search",

abstract = "Large volumes of egocentric video data are being continually collected every day. While the standard video summarisation approach offers all-purpose summaries, here we propose a method for selective video summarisation. The user can query the video with an unlimited vocabulary of terms. The result is a time-tagged summary of keyframes related to the query concept. Our method uses a pre-trained Convolutional Neural Network (CNN) for the semantic search, and visualises the generated summary as a compass. Two commonly used datasets were chosen for the evaluation: UTEgo egocentric video and EDUB lifelog.",

author = "Paria Yousefi and Ludmila Kuncheva",

year = "2018",

language = "English",

note = "The International Image Processing Applications and Systems Conference , IPAS ; Conference date: 12-12-2018 Through 14-12-2018",

}

TY - CONF

T1 - Selective keyframe summarisation for egocentric videos based on semantic concept search

AU - Yousefi, Paria

AU - Kuncheva, Ludmila

PY - 2018

Y1 - 2018

N2 - Large volumes of egocentric video data are being continually collected every day. While the standard video summarisation approach offers all-purpose summaries, here we propose a method for selective video summarisation. The user can query the video with an unlimited vocabulary of terms. The result is a time-tagged summary of keyframes related to the query concept. Our method uses a pre-trained Convolutional Neural Network (CNN) for the semantic search, and visualises the generated summary as a compass. Two commonly used datasets were chosen for the evaluation: UTEgo egocentric video and EDUB lifelog.

AB - Large volumes of egocentric video data are being continually collected every day. While the standard video summarisation approach offers all-purpose summaries, here we propose a method for selective video summarisation. The user can query the video with an unlimited vocabulary of terms. The result is a time-tagged summary of keyframes related to the query concept. Our method uses a pre-trained Convolutional Neural Network (CNN) for the semantic search, and visualises the generated summary as a compass. Two commonly used datasets were chosen for the evaluation: UTEgo egocentric video and EDUB lifelog.

M3 - Paper

T2 - The International Image Processing Applications and Systems Conference

Y2 - 12 December 2018 through 14 December 2018

ER -

Selective keyframe summarisation for egocentric videos based on semantic concept search

Crynodeb

Cynhadledd

Mynediad at Ddogfen

Ôl bys

Dyfynnu hyn