{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T21:01:04Z","timestamp":1760821264679,"version":"3.37.3"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council (ERC) Advanced Grant Commonsense and Anticipation enriched Learning of ContinUous representations supporting Language UnderStanding","doi-asserted-by":"publisher","award":["H2020-ERC-2017-ADG 788506"],"award-info":[{"award-number":["H2020-ERC-2017-ADG 788506"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek (FWO)-Swiss National Science Foundation (SNSF) Grant DEEP LEARNING FOR GENERATING TEMPLATE PICTORIAL AND TEXTUAL REPRESENTATIONS","doi-asserted-by":"publisher","award":["FWO-SNSF G078618N"],"award-info":[{"award-number":["FWO-SNSF G078618N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Artificial Intelligence (AI) Flanders Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3113781","type":"journal-article","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T19:51:52Z","timestamp":1631908312000},"page":"134298-134318","source":"Crossref","is-referenced-by-count":4,"title":["Probing Spatial Clues: Canonical Spatial Templates for Object Relationship Understanding"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1998-8621","authenticated-orcid":false,"given":"Guillem","family":"Collell","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1348-983X","authenticated-orcid":false,"given":"Thierry","family":"Deruyttere","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie-Francine","family":"Moens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1016\/j.tics.2016.09.003"},{"volume-title":"The New Visual Neurosciences","year":"2014","author":"Werner","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1167\/12.13.16"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1167\/4.8.863"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1016\/j.cogpsych.2008.06.001"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1016\/j.visres.2014.08.019"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.3758\/s13423-011-0107-8"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/WACV.2018.00048"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1609\/aaai.v32i1.11939"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1609\/aaai.v31i1.11187"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.18653\/v1\/2020.findings-emnlp.408"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.18653\/v1\/D19-1215"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1609\/aaai.v32i1.12239"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.3115\/v1\/D14-1217"},{"key":"ref15","article-title":"A pooling approach to modelling spatial relations for image retrieval and annotation","volume-title":"arXiv:1411.5190","author":"Malinowski","year":"2014"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1162\/coli.06-78-prep14"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1037\/0096-3445.130.2.273"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1006\/jmla.1997.2519"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.7551\/mitpress\/4107.003.0015"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.18653\/v1\/P19-1230"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/s11263-015-0816-y"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TPAMI.2011.158"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2011.5995631"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPRW.2010.5543176"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/ICCV.2013.390"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR.2010.5540235"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICCV.2009.5459303"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/tpami.2016.2577031"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref30","first-page":"1","article-title":"You only look once: Unified, real-time object detection","volume":"abs\/1506.02640","author":"Redmon","year":"2015","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ICCV.2019.00667"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1007\/978-3-319-46448-0_51"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CVPR.2017.469"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR.2017.470"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/ICCV.2017.121"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICCV.2017.71"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/CVPR.2019.00527"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/CVPR.2017.331"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1007\/978-3-319-46448-0_25"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/ICCV.2015.122"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.24963\/ijcai.2020\/154"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/CVPR42600.2020.01167"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/ICCV.2019.00977"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/CVPR.2019.00370"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/ICCV.2019.00207"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/ICCV.2019.00956"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/ICCV.2019.00579"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1109\/TMM.2019.2943753"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1109\/CVPR.2019.00212"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1109\/ICCV.2019.00093"},{"volume-title":"Proc. BMVC","author":"Gao","article-title":"iCAN: Instance-centric attention network for human-object interaction detection","key":"ref51"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/CVPR.2018.00872"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1007\/978-3-030-01240-3_25"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/WACV.2018.00181"},{"key":"ref55","article-title":"Visual semantic role labeling","volume-title":"arXiv:1505.04474","author":"Gupta","year":"2015"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1007\/978-3-030-01264-9_15"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1609\/aaai.v34i07.6616"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/CVPR.2018.00133"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1109\/ICCV.2013.211"},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.1109\/CVPR42600.2020.00377"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.18653\/v1\/D17-1017"},{"doi-asserted-by":"publisher","key":"ref62","DOI":"10.1109\/CVPR.2017.125"},{"doi-asserted-by":"publisher","key":"ref63","DOI":"10.1109\/IROS.2013.6696569"},{"doi-asserted-by":"publisher","key":"ref64","DOI":"10.1207\/s15427633scc0601_3"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/TPAMI.2009.83"},{"doi-asserted-by":"publisher","key":"ref66","DOI":"10.18653\/v1\/N16-1023"},{"key":"ref67","first-page":"1292","article-title":"Image description using visual dependency representations","volume-title":"Proc. EMNLP","author":"Elliott"},{"doi-asserted-by":"publisher","key":"ref68","DOI":"10.1007\/s11263-016-0981-7"},{"year":"1980","author":"Mitchell","article-title":"The need for biases in learning generalizations","key":"ref69"},{"issue":"1","key":"ref70","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"issue":"1","key":"ref71","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"Fern\u00e1ndez-Delgado","year":"2014","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"publisher","key":"ref72","DOI":"10.1145\/1102351.1102430"},{"doi-asserted-by":"publisher","key":"ref73","DOI":"10.1109\/CVPR.2014.81"},{"doi-asserted-by":"publisher","key":"ref74","DOI":"10.1109\/CVPR.2018.00808"},{"doi-asserted-by":"publisher","key":"ref75","DOI":"10.1109\/CVPR.2018.00142"},{"doi-asserted-by":"publisher","key":"ref76","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref77","article-title":"TrackFormer: Multi-object tracking with transformers","volume-title":"arXiv:2101.02702","author":"Meinhardt","year":"2021"},{"key":"ref78","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"arXiv:1908.08530","author":"Su","year":"2019"},{"key":"ref79","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"arXiv:1908.02265","author":"Lu","year":"2019"},{"doi-asserted-by":"publisher","key":"ref80","DOI":"10.1214\/aos\/1013203451"},{"doi-asserted-by":"publisher","key":"ref81","DOI":"10.1137\/1.9781611974973.1"},{"doi-asserted-by":"publisher","key":"ref82","DOI":"10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"publisher","key":"ref83","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref84","DOI":"10.1007\/978-3-642-00580-0_3"},{"doi-asserted-by":"publisher","key":"ref85","DOI":"10.1007\/s11263-014-0733-5"},{"volume-title":"The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results","author":"Everingham","key":"ref86"},{"doi-asserted-by":"publisher","key":"ref87","DOI":"10.1109\/CVPR.2018.00636"},{"volume-title":"A Faster Pytorch Implementation of Faster R-CNN","year":"2017","author":"Yang","key":"ref88"},{"key":"ref89","article-title":"An implementation of faster RCNN with study for region sampling","volume-title":"arXiv:1702.02138","author":"Chen","year":"2017"},{"key":"ref90","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"doi-asserted-by":"publisher","key":"ref91","DOI":"10.1109\/CVPR.2017.106"},{"doi-asserted-by":"publisher","key":"ref92","DOI":"10.1109\/ICCV.2017.89"},{"doi-asserted-by":"publisher","key":"ref93","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref94","article-title":"OpenPose: Realtime multi-person 2D pose estimation using part affinity fields","volume-title":"arXiv:1812.08008","author":"Cao","year":"2018"},{"doi-asserted-by":"publisher","key":"ref95","DOI":"10.1109\/CVPR.2018.00742"},{"doi-asserted-by":"publisher","key":"ref96","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref97","article-title":"Efficient estimation of word representations in vector space","volume-title":"arXiv:1301.3781","author":"Mikolov","year":"2013"},{"volume-title":"Proc. Int. Conf. Lang. Resour. Eval. (LREC)","author":"Grave","article-title":"Learning word vectors for 157 languages","key":"ref98"},{"key":"ref99","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","volume-title":"arXiv:1907.11692","author":"Liu","year":"2019"},{"doi-asserted-by":"publisher","key":"ref100","DOI":"10.1162\/tacl_a_00134"},{"doi-asserted-by":"publisher","key":"ref101","DOI":"10.1007\/978-3-642-33783-3_10"},{"doi-asserted-by":"publisher","key":"ref102","DOI":"10.5772\/5701"},{"doi-asserted-by":"publisher","key":"ref103","DOI":"10.1109\/CVPR.2008.4587799"},{"doi-asserted-by":"publisher","key":"ref104","DOI":"10.1109\/CVPR.2019.01245"},{"doi-asserted-by":"publisher","key":"ref105","DOI":"10.1109\/TCYB.2020.2989241"},{"doi-asserted-by":"publisher","key":"ref106","DOI":"10.18653\/v1\/W18-1403"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09540850.pdf?arnumber=9540850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:15:12Z","timestamp":1706058912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9540850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3113781","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}