Video Scene Annotation Based on Web Social Activities

Yamamoto, Daisuke; Masuda, T; Ohira, Susumu; Nagao, Katashi

doi:10.1109/mmul.2008.67

Cited by 27 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With no previously formalised method for constructing ThumbReels, we derived a specification by analysing and replicating the frame rates, sizes, and inter-frame delays used in filmstrips. Further, observations suggest that users primarily search for videos using semantic query terms [9] and so we only use these in our preview generation. We break ThumbReel creation into two steps: (1) Tag Processing and, (2) Preview Generation.…”

Section: Creating a Thumbreelmentioning

confidence: 99%

ThumbReels

Craggs

Scott

Alexander

2014

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

During online search, the user's expectations often differ from those of the author. This is known as the 'intention gap' and is particularly problematic when searching for and discriminating between online video content. An author uses description and meta-data tags to label their content, but often cannot predict alternate interpretations or appropriations of their work. To address this intention gap, we present ThumbReels, a concept for query-sensitive video previews generated from crowdsourced, temporally defined semantic tagging. Further, we supply an open-source tool that supports on-the-fly temporal tagging of videos, whose output can be used for later search queries. A first user study validates the tool and concept. We then present a second study that shows participants found ThumbReels to better represent search terms than contemporary preview techniques.

show abstract

Section: Creating a Thumbreelmentioning

confidence: 99%

ThumbReels

Craggs

Scott

Alexander

2014

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…For instance the behavioral (pause, clicks) and annotation data (tags, comments) by users on a video from a soccer game may improve content analysis to both identify game highlights and the semantic of these highlights (goals, opportunities, red cards, penalties, injuries, game conflicts etc). Recent works [14,15] focus on the extraction of video semantics using user activity, establishing the importance of user activity data in semantic inference. Similarly, social multimedia relations mining combined with behavioral and annotation data may lead to better analyze groups and behaviors of the group by segmenting groups according to common behavioral data or other activity data.…”

Section: Taxonomy Of Social Multimedia Miningmentioning

confidence: 99%

Social Multimedia Mining: A Social Informatics Perspective

Lappas¹

2011

2011 15th Panhellenic Conference on Informatics

View full text Add to dashboard Cite

show abstract

“…This interaction behavior provides information about the relevance or appeal of specific portions of the video [66]. The information that users contribute when quoting a scene from a video, commenting on a scene or reaction to others' comments can be exploited to generate annotations [67]. It should be kept in mind, that even basic information about viewing behavior can be extremely helpful for retrieval.…”

Section: Users As Spectators and Joinersmentioning

confidence: 99%

The participation payoff

Ramzan

Larson

Dufaux

et al. 2010

Proceedings of the International Conference on Multimedia Information Retrieval

View full text Add to dashboard Cite

Increasingly, multimedia collections are associated with networked communities consisting of interconnected groups of users who create, annotate, browse, search, share, view, critique and remix collection content. Information arises within networked communities via connections among users and in the course of interactions between users and content. Community-derived information can be exploited to improve user access to multimedia. This paper provides a survey of techniques that make use of a combination of three information sources: communitycontributed information (e.g., tags and ratings), network structure and techniques for multimedia content analysis. This triple synergy offers a wide range of opportunities for improving access to multimedia in networked communities. We focus our survey on three areas important for multimedia access: annotation, distribution and retrieval. The picture that emerges is promising: information derived from the social community is remarkably effective in improving access to multimedia content, and participation in networked communities has a high payoff.

show abstract

Video Scene Annotation Based on Web Social Activities

Cited by 27 publications

References 10 publications

ThumbReels

ThumbReels

Social Multimedia Mining: A Social Informatics Perspective

The participation payoff

Contact Info

Product

Resources

About