{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:08:07Z","timestamp":1777655287129,"version":"3.51.4"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176188"],"award-info":[{"award-number":["62176188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272354"],"award-info":[{"award-number":["62272354"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019035","name":"Key Research and Development Project of Hubei Province","doi-asserted-by":"publisher","award":["2021BAA187"],"award-info":[{"award-number":["2021BAA187"]}],"id":[{"id":"10.13039\/501100019035","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019035","name":"Key Research and Development Project of Hubei Province","doi-asserted-by":"publisher","award":["2022BCA009"],"award-info":[{"award-number":["2022BCA009"]}],"id":[{"id":"10.13039\/501100019035","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Fund of Hubei Luojia Laboratory","award":["220100015"],"award-info":[{"award-number":["220100015"]}]},{"name":"Science and Technology Major Project of Hubei Province","award":["2019AEA170"],"award-info":[{"award-number":["2019AEA170"]}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3261743","type":"journal-article","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T20:41:54Z","timestamp":1680640914000},"page":"2190-2201","source":"Crossref","is-referenced-by-count":17,"title":["Cross-Modality Pyramid Alignment for Visual Intention Understanding"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"first","affiliation":[{"name":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9433-2281","authenticated-orcid":false,"given":"Qinghongya","family":"Shi","sequence":"additional","affiliation":[{"name":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1384-9762","authenticated-orcid":false,"given":"Kehua","family":"Su","sequence":"additional","affiliation":[{"name":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.252"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.282"},{"key":"ref3","first-page":"1","article-title":"PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning","volume-title":"Proc. ACL-IJCNLP","author":"Dopierre"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939801"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377523"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.05.031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1214"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2118"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2035866"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2371532"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108724"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.242"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2437198"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985868"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601263"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172279"},{"key":"ref18","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126535"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3139224"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3131937"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.102"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.423"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820732"},{"key":"ref28","first-page":"3630","article-title":"Predicting the politics of an image using Webly supervised data","volume-title":"Proc. NeurIPS","author":"Thomas"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.352"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.123"},{"key":"ref31","article-title":"Equal but not the same: Understanding the implicit relationship between persuasive images and text","author":"Zhang","year":"2018","journal-title":"arXiv:1807.08205"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2947440"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21236\/ADA612444"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.327"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_19"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00160"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3032542"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102733"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013379"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00822"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"ref55","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"arXiv:1908.02265"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00438"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6824"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2946823"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00397"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00364"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00334"},{"key":"ref62","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","volume-title":"Proc. NeurIPS","author":"Frome"},{"key":"ref63","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. NeurIPS","author":"Karpathy"},{"key":"ref64","article-title":"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data","author":"Qi","year":"2020","journal-title":"arXiv:2001.07966"},{"key":"ref65","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. ICLR","author":"Su"},{"key":"ref66","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref70","article-title":"WenLan: Bridging vision and language by large-scale multi-modal pre-training","author":"Huo","year":"2021","journal-title":"arXiv:2103.06561"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref79","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01558"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"ref82","first-page":"1","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. ICLR","author":"Geirhos"},{"key":"ref83","article-title":"Multi-scale dense networks for resource efficient image classification","volume-title":"Proc. ICLR","author":"Huang"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_1"},{"key":"ref85","article-title":"Object detectors emerge in deep scene CNNs","author":"Zhou","year":"2014","journal-title":"arXiv:1412.6856"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref87","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. ICLR","author":"Lin"},{"key":"ref88","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref89","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_14"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref92","volume-title":"Mindspore","year":"2020"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10092461.pdf?arnumber=10092461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T21:26:30Z","timestamp":1709241990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10092461\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3261743","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}