Symbiosis between the TRECVid benchmark and video libraries at the Netherlands Institute for Sound and Vision

Audiovisual archives are investing in large-scale digitization efforts of their analogue holdings and, in parallel, ingesting an ever-increasing amount of born-digital files in their digital storage facilities. Digitization opens up new access paradigms and boosted re-use of audiovisual content. Query-log analyses show the shortcomings of manual annotation, therefore archives are complementing these annotations by developing novel search engines that automatically extract information from both audio and the visual tracks. Over the past few years, the TRECVid benchmark has developed a novel relationship with the Netherlands Institute of Sound and Vision (NISV) which goes beyond the NISV just providing data and use cases to TRECVid. Prototype and demonstrator systems developed as part of TRECVid are set to become a key driver in improving the quality of search engines at the NISV and will ultimately help other audiovisual archives to offer more efficient and more fine-grained access to their collections. This paper reports the experiences of NISV in leveraging the activities of the TRECVid benchmark.

[1]  Marcel Worring,et al.  On the surplus value of semantic video analysis beyond the key frame , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[2]  W. V. D. van den Heuvel,et al.  Expert search for radio and television: a case study amongst Dutch broadcast professionals , 2010 .

[3]  D. Koelma Any Hope for Cross Any Hope for Cross--Domain Concept Detection Domain Concept Detection in Internet Video? in Internet Video? , 2010 .

[4]  Wietske van den Heuvel Expert search for radio and television: a case study amongst Dutch broadcast professionals , 2010 .

[5]  Marcel Worring,et al.  Concept-Based Video Retrieval , 2009, Found. Trends Inf. Retr..

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

[7]  Michael G. Christel Establishing the utility of non-text search for news video retrieval with real world users , 2007, ACM Multimedia.

[8]  A. Smeulders,et al.  A Multidisciplinary Approach to Unlocking Television Broadcast Archives , 2009 .

[9]  Marcel Worring,et al.  Balancing thread based navigation for targeted video search , 2008, CIVR '08.

[10]  Maarten de Rijke,et al.  Today's and tomorrow's retrieval practice in the audiovisual archive , 2010, CIVR '10.

[11]  Martin Halvey,et al.  Analysis of online video search and sharing , 2007, HT '07.

[12]  Paul Over,et al.  Creating HAVIC: Heterogeneous Audio Visual Internet Collection , 2012, LREC.

[13]  Annemieke de Jong Users, Producers and Other Tags , 2007 .

[14]  Amanda Spink,et al.  A study and comparison of multimedia Web searching: 1997-2006 , 2009, J. Assoc. Inf. Sci. Technol..

[15]  Paul Over,et al.  Video shot boundary detection: Seven years of TRECVid activity , 2010, Comput. Vis. Image Underst..

[16]  Peter G. B. Enser,et al.  Retrieval of Archival Moving Imagery - CBIR Outside the Frame? , 2002, CIVR.

[17]  Albert N. Link,et al.  Economic impact assessment of NIST's text REtrieval conference (TREC) program. Final report , 2010 .

[18]  Alan F. Smeaton,et al.  The scholarly impact of TRECVid (2003-2009) , 2011, J. Assoc. Inf. Sci. Technol..

[19]  Maja Zumer,et al.  FRBR implementation and user research , 2010, ASIST.

[20]  Cees Snoek,et al.  Crowdsourcing rock n' roll multimedia retrieval , 2010, ACM Multimedia.

[21]  Laura Hollink,et al.  Search behavior of media professionals at an audiovisual archive: A transaction log analysis , 2010 .

[22]  Maarten de Rijke,et al.  Content-Based Analysis Improves Audiovisual Archive Retrieval , 2012, IEEE Transactions on Multimedia.

[23]  Hsiao-Tieh Pu,et al.  An analysis of failed queries for web image retrieval , 2008, J. Inf. Sci..

[24]  Ajay Divakaran Multimedia Content Analysis: Theory and Applications , 2008 .

[25]  Sara Shatford,et al.  Analyzing the Subject of a Picture: A Theoretical Approach , 1986 .

[26]  Paul Over,et al.  High-level feature detection from video in TRECVid: a 5-year retrospective of achievements , 2009 .

[27]  Arnold W. M. Smeulders,et al.  Visual-Concept Search Solved? , 2010, Computer.

[28]  Morten Hertzum,et al.  Requests for information from a film archive: a case study of multimedia retrieval , 2003, J. Documentation.