Summarizing the Visual Via the Verbal

By:
To add a paper, Login.

Manual indexing and video annotation, as well as video summarization can be costly and time consuming, taking into account the increasing amount and diversity of multimedia information provided by multimedia production industries. While most automatic film summarization approaches focus on content-based video retrieval, this paper presents a novel method, using different kinds of collateral texts. Such texts describing film content can be freely downloaded on the Internet and provided by organisations producing audio description. A multi-disciplinary approach is suggested, combining cross-document coreference and information extraction techniques, to automatically produce film summaries. The method is inspired by the lexical analysis of a corpus of plot summaries, including short overviews of the film story, and a corpus of audio description, including time-coded detailed descriptions by experts for visually impaired people. The preliminary user evaluation of the method shows encouraging results regarding the precision and ranking of the retrieved video shots. The method may be adapted for different kinds of data and evaluated it in different contexts, such as virtual meeting summarization and browsing.


Keywords: Cross-Document Coreference, Video Summarization, Collateral Text, Information Extraction
Stream: Human Technologies and Usability
Presentation Type: Virtual Presentation in English
Paper: , , , Summarising the Visual via the Verbal


Dr. Eleftheria Tomadaki

The Open University
Milton Keynes, -, UK

Eleftheria Tomadaki is a research fellow in the Knowledge Media Institute (Open University, UK), focusing on collaborative media, e-Learning and social software. Her role involves the integration of the video conferencing tool FlashMeeting with the Moodle e-learning environment and the development of a theory and analytical framework to underpin the study of large-scale synchronous collaborative media, in the context of the Open Content Initiative. She received her PhD in information extraction by the University of Surrey. Her PhD research investigated the merging of information from texts describing video content for video annotation by employing cross-document coreference techniques and introduced a new and challenging scenario - film and the variety of collateral text genres narrating its content, including unrestricted sets of events.

Ref: T08P0193