{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T12:59:15Z","timestamp":1779886755557,"version":"3.53.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/tmm.2018.2812605","type":"journal-article","created":{"date-parts":[[2018,3,9]],"date-time":"2018-03-09T19:17:11Z","timestamp":1520623031000},"page":"2801-2813","source":"Crossref","is-referenced-by-count":164,"title":["Multilabel Image Classification With Regional Latent Semantic Dependencies"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0033-0494","authenticated-orcid":false,"given":"Junjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7240-3541","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9190-507X","authenticated-orcid":false,"given":"Jianfeng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for\n multilingual image question answering","author":"gao","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"203","article-title":"What value do explicit high level concepts have in vision to language problems","author":"wu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref33","first-page":"999","article-title":"Multi-label learning by exploiting label dependency","author":"zhang","year":"0","journal-title":"Proc ACM SIGKDD Int Conf Knowl Discovery Data Mining"},{"key":"ref32","first-page":"195","article-title":"Collective multi-label classification","author":"ghamrawi","year":"0","journal-title":"Proc ACM Conf Inf Knowl Manage"},{"key":"ref31","first-page":"127","article-title":"Learning tree conditional random fields","author":"bradley","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2299516"},{"key":"ref37","first-page":"3156","article-title":"Show and tell: A neural image caption\n generator","author":"vinyals","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref36","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"karpathy","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref35","first-page":"4565","article-title":"Densecap:\n Fully convolutional localization networks for dense captioning","author":"johnson","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref34","first-page":"190","article-title":"Matrix completion for\n multi-label image classification","volume":"201","author":"cabral","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2291218"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref1","first-page":"1097","article-title":"Imagenet\n classification with deep convolutional neural networks","author":"krizhevsky","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(95)00067-4"},{"key":"ref21","first-page":"886","article-title":"Histograms of oriented gradients for human detection","volume":"1","author":"dalal","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref26","first-page":"3286","article-title":"Bing: Binarized normed gradients for\n objectness estimation at 300fps","author":"cheng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref25","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref50","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","first-page":"48","article-title":"Nus-wide: A real-world web image database from\n National University of Singapore","author":"chua","year":"2009","journal-title":"Proc ACM Int Conf Image Video Retrieval"},{"key":"ref57","first-page":"143","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","first-page":"1","article-title":"Weakly supervised object recognition with\n convolutional neural networks","author":"oquab","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","first-page":"25","article-title":"Unified tag analysis with multi-edge graph","author":"liu","year":"0","journal-title":"Proc ACM Conf Multimedia"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2377211"},{"key":"ref53","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref10","first-page":"430","article-title":"Multi-label image\n classification with a probabilistic label enhancement model","author":"li","year":"0","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref11","first-page":"4100","article-title":"Learning graph structure for multi-label image\n classification via clique generation","author":"tan","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref40","first-page":"5","article-title":"Image question Answering: A\n visual semantic embedding model and a new dataset","author":"ren","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2037373"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","first-page":"1045","article-title":"Recurrent neural network based language model","volume":"2","author":"mikolov","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref15","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with\n region proposal networks","author":"ren","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2343217"},{"key":"ref17","first-page":"3426","article-title":"Hierarchical matching with side information for image classification","author":"chen","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref18","first-page":"827","article-title":"Subcategory-aware object classification","author":"dong","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref19","first-page":"237","article-title":"Combining\n efficient object localization and image classification","author":"harzallah","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref4","first-page":"309","article-title":"Tagprop: Discriminative metric learning\n in nearest neighbor models for image auto-annotation","author":"guillaumin","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2306092"},{"key":"ref6","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref5","first-page":"1300","article-title":"Multi-label classification using conditional dependency networks","volume":"22","author":"guo","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref7","first-page":"2285","article-title":"CNN-RNN: A unified framework for multi-label\n image classification","author":"wang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref9","first-page":"1","article-title":"Deep convolutional ranking for multilabel image annotation","volume":"abs 1312 4894","author":"gong","year":"2013","journal-title":"CoRR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref48","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537320"},{"key":"ref42","first-page":"3104","article-title":"Sequence to\n sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"4622","article-title":"Ask me Anything: Free-form visual question answering based on knowledge from\n external sources","author":"wu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref44","first-page":"194","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref43","first-page":"6645","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"0","journal-title":"Proc IEEE Conf Acoust Speech Signal Process"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8466674\/08310600.pdf?arnumber=8310600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:17:13Z","timestamp":1642004233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8310600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":57,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2812605","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}