Main Article Content
Generating compact and intuitive representations of video sequences that can be grasped easily by the users and that let the users quickly browse large amounts of videos is becoming one of the most important topics in content-based video processing. Such representations are called video summaries and these video summaries provide the user with important information about the content of the particular data while preserving the essential message. Here we propose a method to generate video summaries automatically using speech transcripts. We divide the full video into segments based on pause detection (the time duration for which there is a gap in speech) and derive a score for each segment, based on the frequencies of the words and bi-grams it contains. Then, a summary is generated by selecting the segments with the highest score to duration ratios while at the same time maximizing the coverage of the summary over the full program. We developed an experimental design and a user study to judge the quality of the generated video summaries.
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
CC Attribution-NoDerivatives 4.0