Video summarisation based on collaborative temporal tags

Abstract

Purpose -Video summarisation is one of the most active fields in content-based video retrieval research. A new video summarisation scheme is proposed by this paper based on socially generated temporal tags. Design/methodology/approach -To capture users' collaborative tagging activities the proposed scheme maintains video bookmarks, which contain some temporal or positional information about videos, such as relative time codes or byte offsets. For each video all the video bookmarks collected from users are then statistically analysed in order to extract some meaningful key frames (the video equivalent of keywords), which collectively constitute the summary of the video. Findings -Compared with traditional video summarisation methods that use low-level audio-visual features, the proposed method is based on users' high-level collaborative activities, and thus can produce semantically more important summaries than existing methods. Research limitations/implications -It is assumed that the video frames around the bookmarks inserted by users are informative and representative, and therefore can be used as good sources for summarising videos. Originality/value -Folksonomy, commonly called collaborative tagging, is a Web 2.0 method for users to freely annotate shared information resources with keywords. It has mostly been used for collaboratively tagging photos (Flickr), web site bookmarks (Del.icio.us), or blog posts (Technorati), but has never been applied to the field of automatic video summarisation. It is believed that this is the first attempt to utilise users' high-level collaborative tagging activities, instead of low-level audio-visual features, for video summarisation.

Generic speech summarization of transcribed lecture videos: Using tags and their semantic relations

“…They suggested that the proposed method resolved the problem of low coverage of tags faced in previous studies, and users were motivated to add tags by using the tag sharing and tag cloud methods. Having statistically analyzing video bookmarks to form video storyboards, Chung, Wang, and Sheu () extracted some meaningful key frames. In doing so, they assumed that the video frames around bookmarks added by users were sufficiently representative for video summarization.…”

Comparing the use of semantic relations between tags versus latent semantic analysis for generic speech summarization

“…They confirmed that the coverage of annotations generated by the Synvie method was higher than that of existing methods, and users were motivated to add tags by using tag‐sharing and tag‐cloud methods. After statistically analyzing video bookmarks so as to form video storyboards, Chung, Wang, and Sheu (2011) extracted some meaningful key frames. In doing so, they assumed that the video frames around bookmarks added by users were sufficiently representative for video summarization.…”

A tag‐based framework for extracting spoken surrogates

“…Extraction. After statistically analyzing video bookmarks so as to form video storyboards, Chung et al (2011) extract some meaningful key frames; in doing so, they assume that the video frames around bookmarks added by users are representative of and informative enough for video summarization. Their proposed method produced semantically more important summaries than two existing methods that utilize low‐level audio‐visual features.…”