{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T08:17:28Z","timestamp":1775031448720,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/tpami.2019.2893215","type":"journal-article","created":{"date-parts":[[2019,1,16]],"date-time":"2019-01-16T20:10:40Z","timestamp":1547669440000},"page":"1-1","source":"Crossref","is-referenced-by-count":10,"title":["Structured Label Inference for Visual Understanding"],"prefix":"10.1109","author":[{"given":"Nelson Isao","family":"Nauata Junior","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hexiang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang-Tong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicheng","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greg","family":"Mori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref38","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/978-3-642-25446-8_4","article-title":"Sequential deep learning for human action recognition","author":"baccouche","year":"2011","journal-title":"Int Workshop on Human Behavior Understanding"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref28","first-page":"7","article-title":"Combined object categorization and segmentation with an implicit shape model","volume":"2","author":"leibe","year":"2004","journal-title":"Proc ECCV Workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0120-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.455"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1145\/1646396.1646452","article-title":"NUS(National University of Singapore)-wide: A real-world web image database from national university of singapore","author":"chua","year":"2009","journal-title":"Proc ACM Int Conf Image Video Retrieval"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref20","article-title":"Relational inductive biases, deep learning, and graph networks","author":"battaglia","year":"2018"},{"key":"ref22","first-page":"1718","article-title":"Semantic kernel forests from multiple taxonomies","author":"hwang","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref21","first-page":"621","article-title":"Learning a tree of metrics with disjoint visual features","author":"grauman","year":"2011","journal-title":"Proc 24th Int Conf Neural Inf Process Syst"},{"key":"ref24","first-page":"828","article-title":"Image labeling on a network: Using social-network metadata for image classification","author":"mcauley and","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.525"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.249"},{"key":"ref50","first-page":"271","article-title":"A unified semantic embedding: Relating taxonomies and attributes","volume":"1","author":"hwang","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref51","article-title":"Deep convolutional ranking for multilabel image annotation","author":"gong","year":"2013","journal-title":"Arxiv preprint arXiv 1312 4894"},{"key":"ref59","article-title":"Incorporating dictionary and corpus information into a context vector measure of semantic relatedness","author":"patwardhan","year":"2003"},{"key":"ref58","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref57","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref55","first-page":"-647i","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","volume":"32","author":"donahue","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learn"},{"key":"ref54","first-page":"487","article-title":"Learning deep features for scene recognition using places database","volume":"1","author":"zhou","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"ref10","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.138"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.323"},{"key":"ref15","article-title":"Hierarchical label inference for video classification","author":"nauata","year":"2017","journal-title":"arXiv preprint arXiv 1706 05028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","first-page":"567","article-title":"Fast and balanced: Efficient label tree learning for large scale object recognition","author":"deng","year":"2011","journal-title":"Proc 24th Int Conf Neural Inf Process Syst"},{"key":"ref18","first-page":"25","article-title":"Max-margin markov networks","author":"taskar","year":"2003","journal-title":"Proc 16th Int Conf Neural Inf Process Syst"},{"key":"ref19","first-page":"1453","article-title":"Large margin methods for structured and interdependent output variables","volume":"6","author":"tsochantaridis","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref6","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"jiang","year":"2014"},{"key":"ref5","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref8","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref9","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013","journal-title":"arXiv preprint arXiv 1312 6229"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0384-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383131"},{"key":"ref48","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref47","first-page":"545","article-title":"Offline handwriting recognition with multidimensional recurrent neural networks","author":"graves","year":"2009","journal-title":"Proc 21st Int Conf Neural Inf Process Syst"},{"key":"ref42","article-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","author":"montes","year":"2016","journal-title":"arXiv preprint arXiv 1608 08128"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1992.223161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/08613870.pdf?arnumber=8613870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:00:05Z","timestamp":1651068005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8613870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2893215","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}