Generation of Multimedia Artifacts: An Extractive Summarization-based Approach
This addresses the challenge of automated multimedia creation for applications like entertainment and education, but appears incremental as it builds on existing summarization and coherence techniques.
The paper tackles the problem of generating coherent multimedia artifacts by developing an extractive summarization approach for content selection and using emotional music/topic similarity for coherence enhancement, with case studies on film tributes and lecture-driven science talks.
We explore methods for content selection and address the issue of coherence in the context of the generation of multimedia artifacts. We use audio and video to present two case studies: generation of film tributes, and lecture-driven science talks. For content selection, we use centrality-based and diversity-based summarization, along with topic analysis. To establish coherence, we use the emotional content of music, for film tributes, and ensure topic similarity between lectures and documentaries, for science talks. Composition techniques for the production of multimedia artifacts are addressed as a means of organizing content, in order to improve coherence. We discuss our results considering the above aspects.