Support System based on Annotations of Documents and Video Scenes for Reading Technical Documents

PDF
Kentaro ISHITOYA
Graduate School of Information Science, Nagoya University
Keisuke YAMAMOTO
DENSO IT SOLUTIONS
Shigeki OHIRA
Center for Information Media Studies, Nagoya University
Katashi NAGAO
Graduate School of Information Science, Nagoya University

Abstract

Reading as many technical documents as possible is important to improve our research. When we read these documents, we can understand their contents more easily by referring to related resources such as images, audio clips, and videos. Videos contain a variety of helpful information, and facilitate our understanding of technical documents. We propose a method to define video scenes and document elements, and to annotate them with additional information such as relationships. Based on these annotations and relationships, we developed a support system that uses videos and helps readers understand technical documents. We performed some experiments to confirm whether the system was usable.

1

2

3

Overview of reading-support system based on relationships among elements of multimedia contents.

Fugure1: Overview of reading-support system based on relationships among elements of multimedia contents.

3.1

Interface of TDAnnotator.

Fugure2: Interface of TDAnnotator.

3.2

User interface for video scene quotation.

Fugure3: User interface for video scene quotation.

3.3

4

4.1

Relationships among elements of videos and documents.

Fugure6: Relationships among elements of videos and documents.

Data flow of Docvie

Fugure7: Data flow of Docvie

4.2

Document centered mode of Docvie.

Fugure8: Document centered mode of Docvie.

4.3

Video centered mode of Docvie.

Fugure9: Video centered mode of Docvie.

Example questions.

Fugure10: Example questions.

5