{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T22:25:27Z","timestamp":1778019927429,"version":"3.51.4"},"reference-count":126,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010418","name":"Defence Science and Technology Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R018456\/1"],"award-info":[{"award-number":["EP\/R018456\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,4,1]]},"DOI":"10.1109\/tpami.2019.2950025","type":"journal-article","created":{"date-parts":[[2019,10,30]],"date-time":"2019-10-30T20:23:22Z","timestamp":1572467002000},"page":"1404-1422","source":"Crossref","is-referenced-by-count":24,"title":["Visual Semantic Information Pursuit: A Survey"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0475-581X","authenticated-orcid":false,"given":"Daqi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9484-9125","authenticated-orcid":false,"given":"Miroslaw","family":"Bober","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8110-9205","authenticated-orcid":false,"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.71"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019185"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486503"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.555"},{"key":"ref28","first-page":"852","article-title":"Visual relationship detection with language priors","author":"lu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.440"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2745563"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00730"},{"key":"ref101","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"gilmer","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712691"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13890"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2737535"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2739826"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref59","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref57","first-page":"3165","article-title":"Variational algorithms for marginal map","volume":"14","author":"liu","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref56","first-page":"393","article-title":"Convergent message passing algorithms: A unifying view","author":"meltzer","year":"2009","journal-title":"Proc 25th Conf Uncertainty Artif Intell"},{"key":"ref55","first-page":"416","article-title":"Map estimation, linear programming and belief propagation with convex free energies","author":"weiss","year":"2007","journal-title":"Proc 23rd Conf Uncertainty Artif Intell"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1036"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2762355"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.130"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1150"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8579.001.0001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2741510"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1038-2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2642953"},{"key":"ref42","first-page":"346","article-title":"Factorizable net: An efficient subgraph-based framework for scene graph generation","author":"li","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","first-page":"690","article-title":"Graph R-CNN for scene graph generation","author":"yang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","first-page":"558","article-title":"LinkNet: Relational embedding for scene graph","author":"woo","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref43","first-page":"7211","article-title":"Mapping images to scene graphs with permutation-invariant structured prediction","author":"herzig","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.1"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_20"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.554"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4371(99)00291-5"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.68.13"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.141"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.175"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.394"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.850091"},{"key":"ref74","first-page":"467","article-title":"Loopy belief propagation for approximate inference: An empirical study","author":"murphy","year":"1999","journal-title":"Proc 15th Conf Uncertainty Artif Intell"},{"key":"ref75","first-page":"109","article-title":"Efficient inference in fully connected CRFs with gaussian edge potentials","author":"kr\u00e4henb\u00fchl","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref78","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","author":"socher","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref79","first-page":"2152","article-title":"An embarrassingly simple approach to zero-shot learning","author":"romera-paredes","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref60","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000001","article-title":"Graphical models, exponential families, and variational inference","volume":"1","author":"wainwright","year":"2008","journal-title":"Found Trends Mach Learn"},{"key":"ref64","article-title":"Information pursuit: A Bayesian framework for sequential scene parsing","author":"jahangiri","year":"2017"},{"key":"ref65","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref66","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889774"},{"key":"ref2","first-page":"1417","article-title":"Multiple instance boosting for object detection","author":"zhang","year":"2006","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995724"},{"key":"ref1","first-page":"34","article-title":"Robust real-time object detection","volume":"4","author":"viola","year":"2001","journal-title":"Int J Comput Vis"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref95","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.28"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref93","first-page":"513","article-title":"Domain adaptation for large-scale sentiment classification: A deep learning approach","author":"glorot","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref92","first-page":"1476","article-title":"CRVI: Convex relaxation for variational inference","author":"fazelnia","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206536"},{"key":"ref91","first-page":"689","article-title":"Generalized belief propagation","author":"yedidia","year":"2001","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1112-4"},{"key":"ref103","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref102","article-title":"The PASCAL visual object classes challenge 2007 (VOC 2007) results (2007)","author":"everingham","year":"2008"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref98","article-title":"Gated graph sequence neural networks","author":"li","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref99","first-page":"4502","article-title":"Interaction networks for learning about objects, relations and physics","author":"battaglia","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2347059"},{"key":"ref97","first-page":"8964","article-title":"GLoMo: Unsupervised learning of transferable relational graphs","author":"yang","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/2200000013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.04.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"ref13","first-page":"1951","article-title":"What's going on? Discovering spatio-temporal dependencies in dynamic scenes","author":"kuettel","year":"2010","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.33"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2749125"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref82","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","author":"santoro","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref117","first-page":"82","article-title":"Recurrent convolutional neural networks for scene labeling","author":"pinheiro","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref81","article-title":"Neural turing machines","author":"graves","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1228"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref83","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_19"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298977"},{"key":"ref80","first-page":"3630","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.348"},{"key":"ref120","first-page":"2447","article-title":"Recursive context propagation network for semantic scene labeling","author":"sharma","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2535231"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.415"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2533862"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.454"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1173"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298711"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9370031\/08887285.pdf?arnumber=8887285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:13Z","timestamp":1652194153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8887285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":126,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2950025","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":[[2021,4,1]]}}}