SceneMaker: multimodal visualisation of natural language film scripts

E Hanser, P McKevitt, TF Lunney, J Condell, M Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Producing plays, films or animations is a complex and expensive process involving various professionals and media. Our proposed software system, SceneMaker, aims to facilitate this creative process by automatically interpreting natural language film scripts and generating multimodal, animated scenes from them. During the generation of the story content, SceneMaker gives particular attention to emotional aspects and their reflection in fluency and manner of actions, body posture, facial expressions, speech, scene composition, timing, lighting, music and camera work. Related literature and software on Natural Language Processing, in particular textual affect sensing, affective embodied agents, visualisation of 3D scenes and digital cinematography are reviewed. In relation to other work, SceneMaker follows a genre-specific text-to-animation methodology which combines all relevant expressive modalities and is made accessible via web-based and mobile platforms. In conclusion, SceneMaker will enhance the communication of creative ideas providing quick pre-visualisations of scenes.
LanguageEnglish
Title of host publicationUnknown Host Publication
EditorsR Setchi, I Jordanov, RJ Howlett, LC Jain
Place of PublicationHeidelberg, Germany
Pages430-439
Number of pages10
Volume6279
DOIs
Publication statusPublished - Sep 2010
EventProc. of the 14th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (KES-10) - Cardiff University, Cardiff, Wales
Duration: 1 Sep 2010 → …

Conference

ConferenceProc. of the 14th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (KES-10)
Period1/09/10 → …

Fingerprint

Animation
Visualization
Lighting
Cameras
Communication
Processing
Chemical analysis
Cinematography

Cite this

Hanser, E., McKevitt, P., Lunney, TF., Condell, J., & Ma, M. (2010). SceneMaker: multimodal visualisation of natural language film scripts. In R. Setchi, I. Jordanov, RJ. Howlett, & LC. Jain (Eds.), Unknown Host Publication (Vol. 6279, pp. 430-439). Heidelberg, Germany. https://doi.org/10.1007/978-3-642-15384-6_46
Hanser, E ; McKevitt, P ; Lunney, TF ; Condell, J ; Ma, M. / SceneMaker: multimodal visualisation of natural language film scripts. Unknown Host Publication. editor / R Setchi ; I Jordanov ; RJ Howlett ; LC Jain. Vol. 6279 Heidelberg, Germany, 2010. pp. 430-439
@inproceedings{af85100223c8447cbd1edf80bec32705,
title = "SceneMaker: multimodal visualisation of natural language film scripts",
abstract = "Producing plays, films or animations is a complex and expensive process involving various professionals and media. Our proposed software system, SceneMaker, aims to facilitate this creative process by automatically interpreting natural language film scripts and generating multimodal, animated scenes from them. During the generation of the story content, SceneMaker gives particular attention to emotional aspects and their reflection in fluency and manner of actions, body posture, facial expressions, speech, scene composition, timing, lighting, music and camera work. Related literature and software on Natural Language Processing, in particular textual affect sensing, affective embodied agents, visualisation of 3D scenes and digital cinematography are reviewed. In relation to other work, SceneMaker follows a genre-specific text-to-animation methodology which combines all relevant expressive modalities and is made accessible via web-based and mobile platforms. In conclusion, SceneMaker will enhance the communication of creative ideas providing quick pre-visualisations of scenes.",
author = "E Hanser and P McKevitt and TF Lunney and J Condell and M Ma",
year = "2010",
month = "9",
doi = "10.1007/978-3-642-15384-6_46",
language = "English",
isbn = "978-3-642-15383-9",
volume = "6279",
pages = "430--439",
editor = "R Setchi and I Jordanov and RJ Howlett and LC Jain",
booktitle = "Unknown Host Publication",

}

Hanser, E, McKevitt, P, Lunney, TF, Condell, J & Ma, M 2010, SceneMaker: multimodal visualisation of natural language film scripts. in R Setchi, I Jordanov, RJ Howlett & LC Jain (eds), Unknown Host Publication. vol. 6279, Heidelberg, Germany, pp. 430-439, Proc. of the 14th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (KES-10), 1/09/10. https://doi.org/10.1007/978-3-642-15384-6_46

SceneMaker: multimodal visualisation of natural language film scripts. / Hanser, E; McKevitt, P; Lunney, TF; Condell, J; Ma, M.

Unknown Host Publication. ed. / R Setchi; I Jordanov; RJ Howlett; LC Jain. Vol. 6279 Heidelberg, Germany, 2010. p. 430-439.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - SceneMaker: multimodal visualisation of natural language film scripts

AU - Hanser, E

AU - McKevitt, P

AU - Lunney, TF

AU - Condell, J

AU - Ma, M

PY - 2010/9

Y1 - 2010/9

N2 - Producing plays, films or animations is a complex and expensive process involving various professionals and media. Our proposed software system, SceneMaker, aims to facilitate this creative process by automatically interpreting natural language film scripts and generating multimodal, animated scenes from them. During the generation of the story content, SceneMaker gives particular attention to emotional aspects and their reflection in fluency and manner of actions, body posture, facial expressions, speech, scene composition, timing, lighting, music and camera work. Related literature and software on Natural Language Processing, in particular textual affect sensing, affective embodied agents, visualisation of 3D scenes and digital cinematography are reviewed. In relation to other work, SceneMaker follows a genre-specific text-to-animation methodology which combines all relevant expressive modalities and is made accessible via web-based and mobile platforms. In conclusion, SceneMaker will enhance the communication of creative ideas providing quick pre-visualisations of scenes.

AB - Producing plays, films or animations is a complex and expensive process involving various professionals and media. Our proposed software system, SceneMaker, aims to facilitate this creative process by automatically interpreting natural language film scripts and generating multimodal, animated scenes from them. During the generation of the story content, SceneMaker gives particular attention to emotional aspects and their reflection in fluency and manner of actions, body posture, facial expressions, speech, scene composition, timing, lighting, music and camera work. Related literature and software on Natural Language Processing, in particular textual affect sensing, affective embodied agents, visualisation of 3D scenes and digital cinematography are reviewed. In relation to other work, SceneMaker follows a genre-specific text-to-animation methodology which combines all relevant expressive modalities and is made accessible via web-based and mobile platforms. In conclusion, SceneMaker will enhance the communication of creative ideas providing quick pre-visualisations of scenes.

U2 - 10.1007/978-3-642-15384-6_46

DO - 10.1007/978-3-642-15384-6_46

M3 - Conference contribution

SN - 978-3-642-15383-9

VL - 6279

SP - 430

EP - 439

BT - Unknown Host Publication

A2 - Setchi, R

A2 - Jordanov, I

A2 - Howlett, RJ

A2 - Jain, LC

CY - Heidelberg, Germany

ER -

Hanser E, McKevitt P, Lunney TF, Condell J, Ma M. SceneMaker: multimodal visualisation of natural language film scripts. In Setchi R, Jordanov I, Howlett RJ, Jain LC, editors, Unknown Host Publication. Vol. 6279. Heidelberg, Germany. 2010. p. 430-439 https://doi.org/10.1007/978-3-642-15384-6_46