Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/103011
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTran, Duen
dc.contributor.authorYuan, Junsongen
dc.date.accessioned2014-04-07T01:46:24Zen
dc.date.accessioned2019-12-06T21:03:54Z-
dc.date.available2014-04-07T01:46:24Zen
dc.date.available2019-12-06T21:03:54Z-
dc.date.copyright2012en
dc.date.issued2012en
dc.identifier.citationTran, D., & Yuan J. (2012). Max-Margin Structured Output Regression for Spatio-Temporal Action Localization. Advances in Neural Information Processing Systems 25 (NIPS 2012), 1-9.en
dc.identifier.urihttps://hdl.handle.net/10356/103011-
dc.description.abstractStructured output learning has been successfully applied to object localization, where the mapping between an image and an object bounding box can be well captured. Its extension to action localization in videos, however, is much more challenging, because one needs to predict the locations of the action patterns both spatially and temporally, i.e., identifying a sequence of bounding boxes that track the action in video. The problem becomes intractable due to the exponentially large size of the structured video space where actions could occur. We propose a novel structured learning approach for spatio-temporal action localization. The mapping between a video and a spatio-temporal action trajectory is learned. The intractable inference and learning problems are addressed by leveraging an efficient Max-Path search method, thus makes it feasible to optimize the model over the whole structured space. Experiments on two challenging benchmark datasets show that our proposed method outperforms the state-of-the-art methods.en
dc.language.isoenen
dc.rights© 2012 Massachusetts Institute of Technology Press. This paper was published in Advances in Neural Information Processing Systems 25 (NIPS 2012) and is made available as an electronic reprint (preprint) with permission of Massachusetts Institute of Technology Press. The paper can be found at the following official URL: [http://papers.nips.cc/paper/4794-max-margin-structured-output-regression-for-spatio-temporal-action-localization]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.en
dc.subjectDRNTU::Engineering::Electrical and electronic engineeringen
dc.titleMax-margin structured output regression for spatio-temporal action localizationen
dc.typeConference Paperen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen
dc.contributor.conferenceAdvances in Neural Information Processing Systems 25 (NIPS 2012)en
dc.identifier.openurlhttp://papers.nips.cc/paper/4794-max-margin-structured-output-regression-for-spatio-temporal-action-localizationen
dc.description.versionPublished versionen
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:EEE Conference Papers
Files in This Item:
File Description SizeFormat 
Max-Margin Structured Output Regression for Spatio-Temporal Action Localization.pdf8.02 MBAdobe PDFThumbnail
View/Open

Page view(s) 50

385
Updated on Apr 14, 2021

Download(s) 10

365
Updated on Apr 14, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.