Measuring the impact of temporal context on video retrieval

In this paper we describe the findings from the K-Space interactive video search experiments in TRECVid 2007, which examined the effects of including temporal context in video retrieval. The traditional approach to presenting video search results is to maximise recall by offering a user as many potentially relevant shots as possible within a limited amount of time. 'Context'-oriented systems opt to allocate a portion of the results presentation space to providing additional contextual cues about the returned results. In video retrieval these cues often include temporal information such as a shot's location within the overall video broadcast and/or its neighbouring shots. We developed two interfaces with identical retrieval functionality in order to measure the effects of such context on user performance. The first system had a 'recall-oriented' interface, where results from a query were presented as a ranked list of shots. The second was 'context-oriented', with results presented as a ranked list of broadcasts. 10 users participated in the experiments, of which 8 were novices and 2 experts. Participants completed a number of retrieval topics using both the recall-oriented and context-oriented systems.

[1]  Alan F. Smeaton,et al.  The Físchlár-News-Stories System: Personalised Access to an Archive of TV News , 2004, RIAO.

[2]  Paul Over,et al.  Evaluation campaigns and TRECVid , 2006, MIR '06.

[3]  Marcel Worring,et al.  Adding Semantics to Detectors for Video Retrieval , 2007, IEEE Transactions on Multimedia.

[4]  Marcel Worring,et al.  MediaMill: semantic video search using the RotorBrowser , 2007, CIVR '07.

[5]  Alan F. Smeaton,et al.  TRECVID 2004 Experiments in Dublin City University , 2004, TRECVID.

[6]  Noel E. O'Connor,et al.  Using Dempster-Shafer Theory to Fuse Multiple Information Sources in Region-Based Segmentation , 2007, 2007 IEEE International Conference on Image Processing.

[7]  Dennis Koelma,et al.  The MediaMill TRECVID 2008 Semantic Video Search Engine , 2008, TRECVID.

[8]  Yiannis Kompatsiaris,et al.  K-Space at TRECvid 2006 , 2006, TRECVID.

[9]  Alan F. Smeaton,et al.  Fischlár @ TRECVID2003: system description , 2004, MULTIMEDIA '04.

[10]  Marcel Worring,et al.  MediaMill: Semantic Video Browsing using the RotorBrowser , 2007 .

[11]  Paul Over,et al.  TRECVID: evaluating the effectiveness of information retrieval tasks on digital video , 2004, MULTIMEDIA '04.

[12]  John R. Smith,et al.  IBM Research TRECVID-2009 Video Retrieval System , 2009, TRECVID.

[13]  Paul Over,et al.  TRECVID 2007--Overview , 2007, TRECVID.

[14]  Jun Yang,et al.  Exploring temporal consistency for video analysis and retrieval , 2006, MIR '06.

[15]  Paul Over,et al.  TRECVID: Benchmarking the Effectivenss of Information Retrieval Tasks on Digital Video , 2003, CIVR.

[16]  Alan F. Smeaton,et al.  Design, implementation and testing of an interactive video retrieval system , 2003, MIR '03.

[17]  Alexander G. Hauptmann,et al.  Successful approaches in the TREC video retrieval evaluations , 2004, MULTIMEDIA '04.

[18]  João Magalhães,et al.  Video Retrieval Using Search and Browsing , 2004, TRECVID.