Interactive storytelling via video content recombination

Julie Porteous; Sergio Benini; Luca Canini; Fred Charles; Marc Cavazza; Riccardo Leonardi

doi:10.1145/1873951.1874334

Interactive storytelling via video content recombination

Julie Porteous, Sergio Benini, Luca Canini, Fred Charles, Marc Cavazza, Riccardo Leonardi

SCEDT School Executive Team

Research output: Contribution to conference › Paper › peer-review

312 Downloads (Pure)

Abstract

In the paper we present a prototype of video-based storytelling that is able to generate multiple story variants from a baseline video. The video content for the system is generated by an adaptation of forefront video summarisation techniques that decompose the video into a number of Logical Story Units (LSU) representing sequences of contiguous and interconnected shots sharing a common semantic thread. Alternative storylines are generated using AI Planning techniques and these are used to direct the combination of elementary LSU for output. We report early results from experiments with the prototype in which the reordering of video shots on the basis of their high-level semantics produces trailers giving the illusion of different storylines.

Original language	English
Pages	1715-1718
DOIs	https://doi.org/10.1145/1873951.1874334
Publication status	Published - 2010
Event	MM '10 ACM Multimedia Conference - Firenze, Italy Duration: 25 Oct 2010 → 29 Oct 2010

Conference

Conference	MM '10 ACM Multimedia Conference
Country/Territory	Italy
City	Firenze
Period	25/10/10 → 29/10/10

Access to Document

10.1145/1873951.1874334

Full textAccepted author manuscript, 1.06 MBLicence: CC BY-NC-ND

http://dl.acm.org/citation.cfm?doid=1873951.1874334

Cite this

@conference{ded6adca826842c4b070b3aa816ce8be,

title = "Interactive storytelling via video content recombination",

abstract = "In the paper we present a prototype of video-based storytelling that is able to generate multiple story variants from a baseline video. The video content for the system is generated by an adaptation of forefront video summarisation techniques that decompose the video into a number of Logical Story Units (LSU) representing sequences of contiguous and interconnected shots sharing a common semantic thread. Alternative storylines are generated using AI Planning techniques and these are used to direct the combination of elementary LSU for output. We report early results from experiments with the prototype in which the reordering of video shots on the basis of their high-level semantics produces trailers giving the illusion of different storylines.",

author = "Julie Porteous and Sergio Benini and Luca Canini and Fred Charles and Marc Cavazza and Riccardo Leonardi",

year = "2010",

doi = "10.1145/1873951.1874334",

language = "English",

pages = "1715--1718",

note = "MM '10 ACM Multimedia Conference ; Conference date: 25-10-2010 Through 29-10-2010",

}

TY - CONF

T1 - Interactive storytelling via video content recombination

AU - Porteous, Julie

AU - Benini, Sergio

AU - Canini, Luca

AU - Charles, Fred

AU - Cavazza, Marc

AU - Leonardi, Riccardo

PY - 2010

Y1 - 2010

N2 - In the paper we present a prototype of video-based storytelling that is able to generate multiple story variants from a baseline video. The video content for the system is generated by an adaptation of forefront video summarisation techniques that decompose the video into a number of Logical Story Units (LSU) representing sequences of contiguous and interconnected shots sharing a common semantic thread. Alternative storylines are generated using AI Planning techniques and these are used to direct the combination of elementary LSU for output. We report early results from experiments with the prototype in which the reordering of video shots on the basis of their high-level semantics produces trailers giving the illusion of different storylines.

AB - In the paper we present a prototype of video-based storytelling that is able to generate multiple story variants from a baseline video. The video content for the system is generated by an adaptation of forefront video summarisation techniques that decompose the video into a number of Logical Story Units (LSU) representing sequences of contiguous and interconnected shots sharing a common semantic thread. Alternative storylines are generated using AI Planning techniques and these are used to direct the combination of elementary LSU for output. We report early results from experiments with the prototype in which the reordering of video shots on the basis of their high-level semantics produces trailers giving the illusion of different storylines.

U2 - 10.1145/1873951.1874334

DO - 10.1145/1873951.1874334

M3 - Paper

SP - 1715

EP - 1718

T2 - MM '10 ACM Multimedia Conference

Y2 - 25 October 2010 through 29 October 2010

ER -

Interactive storytelling via video content recombination

Abstract

Conference

Access to Document

Fingerprint

Cite this