Show simple item record

dc.contributor.authorAksoy, Selimen_US
dc.contributor.authorÇavuş Özgeen_US
dc.coverage.spatialBelgrade, Serbia
dc.date.accessioned2016-02-08T11:51:29Z
dc.date.available2016-02-08T11:51:29Z
dc.date.issued2005-11en_US
dc.identifier.urihttp://hdl.handle.net/11693/27365
dc.descriptionDate of Conference: 21-24 Nov. 2005
dc.descriptionConference name: EUROCON 2005 - The International Conference on "Computer as a Tool"
dc.description.abstractContent-based retrieval in news video databases has become an important task with the availability of large quantities of data in both public and proprietary archives. We describe a relevance feedback technique that captures the significance of different features at different spatial locations in an image. Spatial content is modeled by partitioning images into non-overlapping grid cells. Contributions of different features at different locations are modeled using weights defined for each feature in each grid cell. These weights are iteratively updated based on user's feedback in terms of positive and negative labeling of retrieval results. Given this labeling, the weight updating scheme uses the ratios of standard deviations of the distances between relevant and irrelevant images to the standard deviations of the distances between relevant images. The proposed technique is quantitatively and qualitatively evaluated using shots related to several sports from the news video collection of the TRECVID video retrieval evaluation where the weights could capture relative contributions of different features and spatial locations. © 2005 IEEE.en_US
dc.language.isoEnglishen_US
dc.source.titleEUROCON 2005 - The International Conference on Computer as a Toolen_US
dc.relation.isversionofhttps://doi.org/10.1109/EURCON.2005.1629878
dc.subjectNews videosen_US
dc.subjectRelevance feedbacken_US
dc.subjectSports videosen_US
dc.subjectTRECVIDen_US
dc.subjectVideo retrievalen_US
dc.subjectComputer simulationen_US
dc.subjectFeature extractionen_US
dc.subjectFeedback controlen_US
dc.subjectImage analysisen_US
dc.subjectVideo signal processingen_US
dc.subjectContent based retrievalen_US
dc.titleA relevance feedback technique for multimodal retrieval of news videosen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineering
dc.citation.spage139en_US
dc.citation.epage142en_US
dc.identifier.doi10.1109/EURCON.2005.1629878
dc.publisherIEEE


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record