부산대학교 도서관

In recent years, there has been a massive increase in multimedia data due to the increasing use of social media and communication technology. So, extracting useful information from a large set of data has become difficult and very time consuming. Multimedia Data (Text, Image, Audio, Video) summarization is a very useful technology that overcomes this challenge by eliminating information that is redundant or useless, and extracting only the relevant key details of the events in summaries. A lot of work has been done in this field to generate summaries in the form of text and images, but very limited research has been done to produce a multimodular summary especially on Asynchronous Data. This research work proposes an ILP based model, which takes a multimodal dataset (text, images, videos) as input and generates textual and image video summary as output. The results were obtained by comparing the two basic baseline’s ROUGE values with the proposed model. Results for different modalities have confirmed that the proposed model performs better than the other baseline approaches.