A relevance feedback approach to video genre retrieval

Content-based retrieval in video databases has become an important task with the availability of large quantities of data in both public and proprietary archives. Most of video systems are based on feature classification, but problems appear because of “semantic gap” between high-level human concepts and the machine-readable low-level visual features. In this paper we adopt a relevance feedback approach (RF) to bridge the semantic gap by progressively collecting feedback from the user, which allows the machine to discover the semantic meanings of objects or events. Experimental tests conducted on more than 91 hours of video footage show an improvement of up to 90% in retrieval accuracy, compared to classic classification-based retrieval.

[1]  Richard M. Stern,et al.  Speech in Noisy Environments: robust automatic segmentation, feature extraction, and hypothesis combination , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[2]  B. S. Manjunath,et al.  Color and texture descriptors , 2001, IEEE Trans. Circuits Syst. Video Technol..

[3]  Shuang Liang,et al.  Sketch retrieval and relevance feedback with biased SVM classification , 2008, Pattern Recognit. Lett..

[4]  Simone Santini,et al.  Exploratory Image Databases: Content-Based Retrieval , 2001 .

[5]  S Hancocks,et al.  I go to a friend , 2001, British dental journal.

[6]  Christoph Rasche,et al.  An Approach to the Parameterization of Structure for Fast Categorization , 2010, International Journal of Computer Vision.

[7]  José M. Martínez.  Standards - MPEG-7 overview of MPEG-7 description tools, part 2 , 2002 .

[8]  Gerard Salton,et al.  The SMART Retrieval System—Experiments in Automatic Document Processing , 1971 .

[9]  Stephen E. Robertson,et al.  Okapi at TREC-3 , 1994, TREC.

[10]  Stephen E. Robertson,et al.  GatfordCentre for Interactive Systems ResearchDepartment of Information , 1996 .

[11]  Brian Everitt,et al.  Principles of Multivariate Analysis , 2001 .

[12]  S. Aksoy,et al.  A Relevance Feedback Technique for Multimodal Retrieval of News Videos , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".

[13]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[14]  Nicolas Maillot,et al.  Ontology Based Object Learning and Recognition , 2005 .

[15]  James R. Schott,et al.  Principles of Multivariate Analysis: A User's Perspective , 2002 .

[16]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[17]  Alan F. Smeaton,et al.  Using video objects and relevance feedback in video retrieval , 2005, SPIE Optics East.

[18]  Rujie Liu,et al.  SVM-based active feedback in image retrieval using clustering and unlabeled data , 2008, Pattern Recognit..

[19]  Marcel Worring,et al.  Multimodal Video Indexing : A Review of the State-ofthe-art , 2001 .

[20]  Patrick Lambert,et al.  A Fuzzy Color-Based Approach for Understanding Animated Movies Content in the Indexing Task , 2008, EURASIP J. Image Video Process..

[21]  Thomas S. Huang,et al.  Relevance feedback: a power tool for interactive content-based image retrieval , 1998, IEEE Trans. Circuits Syst. Video Technol..

[22]  Ellen K. Hughes,et al.  Video OCR for digital news archive , 1998, Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database.