{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T02:00:03Z","timestamp":1779933603731,"version":"3.53.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1651902"],"award-info":[{"award-number":["1651902"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-17-1-0367"],"award-info":[{"award-number":["W911NF-17-1-0367"]}],"id":[{"id":"10.13039\/100000183","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":[[2023,1,1]]},"DOI":"10.1109\/tpami.2022.3148470","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T21:04:55Z","timestamp":1644267895000},"page":"641-656","source":"Crossref","is-referenced-by-count":129,"title":["Image-Text Embedding Learning via Visual and Textual Semantic Reasoning"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5805-793X","authenticated-orcid":false,"given":"Kunpeng","family":"Li","sequence":"first","affiliation":[{"name":"Facebook Reality Labs, Burlingame, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2288-5079","authenticated-orcid":false,"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Vision Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"NEC Laboratories America Inc., Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2851-8528","authenticated-orcid":false,"given":"Yuanyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5098-2853","authenticated-orcid":false,"given":"Yun","family":"Fu","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"ref72","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"cuturi","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref71","article-title":"Ranking via sinkhorn propagation","author":"adams","year":"2011"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1967.21.343"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2883466"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"ref78","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","author":"gan","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref32","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref37","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref60","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref62","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref64","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247671"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref29","first-page":"1","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.38"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref1","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref20","first-page":"1","article-title":"Deep graph matching consensus","author":"fey","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref24","first-page":"595","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume":"32","author":"kiros","year":"2015","journal-title":"Trans Assoc Comput Linguistics"},{"key":"ref23","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref26","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(90)90087-6"},{"key":"ref51","first-page":"529","article-title":"Random walk inference and learning in a large scale knowledge base","author":"lao","year":"2011","journal-title":"Proc Conf Empir Methods Natural Lang Process"},{"key":"ref59","first-page":"5669","article-title":"Connective cognition network for directional visual commonsense reasoning","author":"wu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","first-page":"2769","article-title":"Heterogeneous graph learning for visual commonsense reasoning","author":"yu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref57","first-page":"1","article-title":"Visual semantic navigation using scene priors","author":"yang","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.650"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.546"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00604"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/1073858413514136"},{"key":"ref15","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":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018489"},{"key":"ref16","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref81","first-page":"1542","article-title":"Graph optimal transport for cross-domain alignment","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref83","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/720"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref7","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(93)90015-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01254"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2921543"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0402_2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00530"},{"key":"ref42","first-page":"1","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Learn Representations Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.338"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9970415\/9706340-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9970415\/09706340.pdf?arnumber=9706340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:13:15Z","timestamp":1672081995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9706340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":83,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3148470","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":[[2023,1,1]]}}}