Automatic multimedia cross-modal correlation discovery

Simple item page
dc.citation.epage658en_US
dc.citation.spage653en_US
dc.contributor.authorPan, J.-Y.en_US
dc.contributor.authorYang, H.-J.en_US
dc.contributor.authorFaloutsos, C.en_US
dc.contributor.authorDuygulu, Pınaren_US
dc.coverage.spatialSeattle, WA, USA
dc.date.accessioned2016-02-08T11:53:08Z
dc.date.available2016-02-08T11:53:08Z
dc.date.issued2004-08en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 22-25 August , 2004
dc.descriptionConference name: KDD '04 Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
dc.description.abstractGiven an image (or video clip, or audio song), how do we automatically assign keywords to it? The general problem is to find correlations across the media in a collection of multimedia objects like video clips, with colors, and/or motion, and/or audio, and/or text scripts. We propose a novel, graph-based approach, "MMG", to discover such cross-modal correlations. Our "MMG" method requires no tuning, no clustering, no user-determined constants; it can be applied to any multi-media collection, as long as we have a similarity function for each medium; and it scales linearly with the database size. We report auto-captioning experiments on the "standard" Corel image database of 680 MB, where it outperforms domain specific, fine-tuned methods by up to 10 percentage points in captioning accuracy (50% relative improvement).en_US
dc.identifier.doi10.1145/1014052.1014135
dc.identifier.urihttp://hdl.handle.net/11693/27429
dc.language.isoEnglishen_US
dc.publisherACM
dc.relation.isversionofhttps://doi.org/10.1145/1014052.1014135
dc.source.titleKDD-2004 - Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Miningen_US
dc.subjectAutomatic image captioningen_US
dc.subjectCross-modal correlationen_US
dc.subjectGraph-based modelen_US
dc.subjectApproximation theoryen_US
dc.subjectCorrelation methodsen_US
dc.subjectDatabase systemsen_US
dc.subjectGraph theoryen_US
dc.subjectImage analysisen_US
dc.subjectMathematical modelsen_US
dc.subjectMotion estimationen_US
dc.subjectProbabilityen_US
dc.subjectProblem solvingen_US
dc.subjectAutomatic image captioningen_US
dc.subjectCross-modal correlationen_US
dc.subjectGraph-based modelsen_US
dc.subjectVideo motionen_US
dc.subjectMultimedia systemsen_US
dc.titleAutomatic multimedia cross-modal correlation discoveryen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Automatic multimedia cross-modal correlation discovery.pdf
Size:
135.44 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Computer Engineering