UPRISE: Unified Presentation Slide Retrieval by Impression Search Engine

Haruo YOKOTA; Takashi KOBAYASHI; Taichi MURAKI; Satoshi NAOI

UPRISE: Unified Presentation Slide Retrieval by Impression Search Engine

Haruo YOKOTA, Takashi KOBAYASHI, Taichi MURAKI, Satoshi NAOI

Full Text Views

0

Cite this

Summary :

A combination of slides used in a presentation and a video recording of the circumstances of the presentation are quite useful for many applications, such as e-learning. However, to create new content from these with current authoring tools requires considerable effort for the author and the products have reduced flexibility. In this paper, we propose the preparation of a unifying function without creating new content manually. We also propose a new approach to search unified presentation manuscripts for slides matched with given keywords by considering the features peculiar to the presentation slides. We propose impression indicators to express how well a slide matches the given keywords. We also propose a system for retrieving a sequence of desired presentation slides from archives of the combined slides and video. We named the system Unified Presentation Slide Retrieval by Impression Search Engine or UPRISE. We describe the system configuration of UPRISE and the experimentation undertaken to evaluate the effect of the proposed indicators and to compare the results with those of the traditional tf.idf retrieval method.

Publication: IEICE TRANSACTIONS on Information Vol.E87-D No.2 pp.397-406

Publication Date: 2004/02/01

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section on Information Processing Technology for Web Utilization)

Category

Cite this

Copy

Haruo YOKOTA, Takashi KOBAYASHI, Taichi MURAKI, Satoshi NAOI, "UPRISE: Unified Presentation Slide Retrieval by Impression Search Engine" in IEICE TRANSACTIONS on Information, vol. E87-D, no. 2, pp. 397-406, February 2004, doi: .
Abstract: A combination of slides used in a presentation and a video recording of the circumstances of the presentation are quite useful for many applications, such as e-learning. However, to create new content from these with current authoring tools requires considerable effort for the author and the products have reduced flexibility. In this paper, we propose the preparation of a unifying function without creating new content manually. We also propose a new approach to search unified presentation manuscripts for slides matched with given keywords by considering the features peculiar to the presentation slides. We propose impression indicators to express how well a slide matches the given keywords. We also propose a system for retrieving a sequence of desired presentation slides from archives of the combined slides and video. We named the system Unified Presentation Slide Retrieval by Impression Search Engine or UPRISE. We describe the system configuration of UPRISE and the experimentation undertaken to evaluate the effect of the proposed indicators and to compare the results with those of the traditional tf.idf retrieval method.
URL: https://global.ieice.org/en_transactions/information/10.1587/e87-d_2_397/_p

Copy

@ARTICLE{e87-d_2_397,
author={Haruo YOKOTA, Takashi KOBAYASHI, Taichi MURAKI, Satoshi NAOI, },
journal={IEICE TRANSACTIONS on Information},
title={UPRISE: Unified Presentation Slide Retrieval by Impression Search Engine},
year={2004},
volume={E87-D},
number={2},
pages={397-406},
abstract={A combination of slides used in a presentation and a video recording of the circumstances of the presentation are quite useful for many applications, such as e-learning. However, to create new content from these with current authoring tools requires considerable effort for the author and the products have reduced flexibility. In this paper, we propose the preparation of a unifying function without creating new content manually. We also propose a new approach to search unified presentation manuscripts for slides matched with given keywords by considering the features peculiar to the presentation slides. We propose impression indicators to express how well a slide matches the given keywords. We also propose a system for retrieving a sequence of desired presentation slides from archives of the combined slides and video. We named the system Unified Presentation Slide Retrieval by Impression Search Engine or UPRISE. We describe the system configuration of UPRISE and the experimentation undertaken to evaluate the effect of the proposed indicators and to compare the results with those of the traditional tf.idf retrieval method.},
keywords={},
doi={},
ISSN={},
month={February},}

Copy

TY - JOUR
TI - UPRISE: Unified Presentation Slide Retrieval by Impression Search Engine
T2 - IEICE TRANSACTIONS on Information
SP - 397
EP - 406
AU - Haruo YOKOTA
AU - Takashi KOBAYASHI
AU - Taichi MURAKI
AU - Satoshi NAOI
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E87-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2004
AB - A combination of slides used in a presentation and a video recording of the circumstances of the presentation are quite useful for many applications, such as e-learning. However, to create new content from these with current authoring tools requires considerable effort for the author and the products have reduced flexibility. In this paper, we propose the preparation of a unifying function without creating new content manually. We also propose a new approach to search unified presentation manuscripts for slides matched with given keywords by considering the features peculiar to the presentation slides. We propose impression indicators to express how well a slide matches the given keywords. We also propose a system for retrieving a sequence of desired presentation slides from archives of the combined slides and video. We named the system Unified Presentation Slide Retrieval by Impression Search Engine or UPRISE. We describe the system configuration of UPRISE and the experimentation undertaken to evaluate the effect of the proposed indicators and to compare the results with those of the traditional tf.idf retrieval method.
ER -