Show simple item record

dc.contributor.authorKuehne, H.
dc.contributor.authorSerre, T.
dc.contributor.authorJhuang, H.
dc.contributor.authorGarrote, Estibaliz
dc.contributor.authorPoggio, Tomaso A.
dc.date.accessioned2012-04-11T17:45:39Z
dc.date.available2012-04-11T17:45:39Z
dc.date.issued2012-01
dc.date.submitted2011-11
dc.identifier.isbn978-1-4577-1101-5
dc.identifier.issn1550-5499
dc.identifier.otherINSPEC Accession Number: 12491176
dc.identifier.urihttp://hdl.handle.net/1721.1/69981
dc.description.abstractWith nearly one billion online videos viewed everyday, an emerging new frontier in computer vision research is recognition and search in video. While much effort has been devoted to the collection and annotation of large scalable static image datasets containing thousands of image categories, human action datasets lag far behind. Current action recognition databases contain on the order of ten different action categories collected under fairly controlled conditions. State-of-the-art performance on these datasets is now near ceiling and thus there is a need for the design and creation of new benchmarks. To address this issue we collected the largest action video database to-date with 51 action categories, which in total contain around 7,000 manually annotated clips extracted from a variety of sources ranging from digitized movies to YouTube. We use this database to evaluate the performance of two representative computer vision systems for action recognition and explore the robustness of these methods under various conditions such as camera motion, viewpoint, video quality and occlusion.en_US
dc.description.sponsorshipUnited States. Defense Advanced Research Projects Agency. Information Processing Techniques Officeen_US
dc.description.sponsorshipUnited States. Defense Advanced Research Projects Agency. System Science Division. Defense Sciences Officeen_US
dc.description.sponsorshipNational Science Foundation (U.S.) (NSF-0640097)en_US
dc.description.sponsorshipNational Science Foundation (U.S.) (NSF-0827427)en_US
dc.description.sponsorshipUnited States. Air Force Office of Scientific Research (FA8650-05- C-7262)en_US
dc.description.sponsorshipAdobe Systemsen_US
dc.description.sponsorshipKing Abdullah University of Science and Technologyen_US
dc.description.sponsorshipNEC Electronicsen_US
dc.description.sponsorshipSony Corporationen_US
dc.description.sponsorshipEugene McDermott Foundationen_US
dc.description.sponsorshipBrown University. Center for Computing and Visualizationen_US
dc.description.sponsorshipRobert J. and Nancy D. Carney Fund for Scientific Innovationen_US
dc.description.sponsorshipUnited States. Defense Advanced Research Projects Agency (DARPA-BAA-09-31)en_US
dc.description.sponsorshipUnited States. Office of Naval Research (ONR-BAA-11-001)en_US
dc.description.sponsorshipMinistry of Science, Research and the Arts of Baden Württemberg, Germanyen_US
dc.language.isoen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/ICCV.2011.6126543en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alike 3.0en_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/en_US
dc.sourceProf. Poggioen_US
dc.titleHMDB: A Large Video Database for Human Motion Recognitionen_US
dc.typeArticleen_US
dc.identifier.citationKuehne, H. et al. “HMDB: A Large Video Database for Human Motion Recognition.” IEEE, 2011. 2556–2563. Web. 11 Apr. 2012. © 2012 Institute of Electrical and Electronics Engineersen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Brain and Cognitive Sciencesen_US
dc.contributor.approverPoggio, Tomaso A.
dc.contributor.mitauthorJhuang, H.
dc.contributor.mitauthorGarrote, Estibaliz
dc.contributor.mitauthorPoggio, Tomaso A.
dc.relation.journal2011 IEEE International Conference on Computer Visionen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
dspace.orderedauthorsKuehne, H.; Jhuang, H.; Garrote, E.; Poggio, T.; Serre, T.en
dc.identifier.orcidhttps://orcid.org/0000-0002-3944-0455
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record