Finding a needle in a haystack: an interactive video archive explorer for professional video searchers

Abstract

Abstract1 Professional video searchers typically have to search for particular video fragments in a vast video archive that contains many hours of video data. Without having the right video archive exploration tools, this is a difficult and time consuming task that induces hours of video skimming. We propose the video archive explorer, a video exploration tool that provides visual representations of automatically detected concepts to facilitate individual and collaborative video search tasks. This video archive explorer is developed by employing a user-centred methodology, which ensures that the tool is more likely to fit to the end user needs. A qualitative evaluation with professional video searchers shows that the combination of automatic video indexing, interactive visualisations and user-centred design can result in an increased usability, user satisfaction and productivity.

Visual, Laughter, Applause and Spoken Expression Features for Predicting Engagement Within TED Talks

“…In terms of video content, researchers have described user engagement with video content in a variety of ways, e.g. duration for which a user watches a video [5,6] and subjective evaluation of user engagement through questionnaires [7,8]. It can be seen that there is not much agreement in measuring engagement due to its highly context dependent nature.…”

“…An example of comprehensive multimodal feature extraction is the work of Evangelopoulos et al who take advantage of all three visual, audio and linguistic modalities to create video summaries [16]. Other interesting examples of multimodal feature extraction are work of Dong et al [17] and Haesen et al [8]. Extracting all these multimodal features and indexing them would make videos more searchable and would also help correlate videos with user feedback, and thereby user engagement.…”

Video Interaction Tools

“…The Video Archive Explorer proposed by Haesen et al [2013] allows one to physically and collaboratively explore videos on a multitouch tablet through interactive content visualizations. A search starts with entering a textual query.…”

The value of information cues for lifelog video navigation

“…Researchers explored alternative ways of video navigation. Examples are different time-based video arrangements, such as a clock-based arrangement of video frame thumb nails [10] or slit scans reducing a frame, for example, to a pixel column and creating slit scan frames out of several of these pixel columns [14]. 2D storyboard arrangement were used to give an overview of the video content via thumb nails [2,4,6,11,17].…”