{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:00:43Z","timestamp":1782403243921,"version":"3.54.5"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LQ22F020006"],"award-info":[{"award-number":["LQ22F020006"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61922064"],"award-info":[{"award-number":["61922064"]}],"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":["U2033210"],"award-info":[{"award-number":["U2033210"]}],"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":["62101387"],"award-info":[{"award-number":["62101387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3148867","type":"journal-article","created":{"date-parts":[[2022,3,11]],"date-time":"2022-03-11T20:24:31Z","timestamp":1647030271000},"page":"2570-2583","source":"Crossref","is-referenced-by-count":77,"title":["SST: Spatial and Semantic Transformers for Multi-Label Image Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8955-1789","authenticated-orcid":false,"given":"Zhao-Min","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3428-4913","authenticated-orcid":false,"given":"Quan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Borui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3076-1786","authenticated-orcid":false,"given":"Renjie","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0958-7285","authenticated-orcid":false,"given":"Xiaoqin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4192-554X","authenticated-orcid":false,"given":"Osamu","family":"Yoshie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref4","first-page":"649","article-title":"Attention-driven dynamic graph convolutional network for multi-label image recognition","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Jin"},{"key":"ref5","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref7","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"arXiv:1906.08237","author":"Yang","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.199"},{"key":"ref11","article-title":"Deep convolutional ranking for multilabel image annotation","volume-title":"arXiv:1312.4894","author":"Gong","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.37"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.323"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref16","first-page":"1","article-title":"Cross-modality attention with semantic graph embedding for multi-label classification","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Renchun"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00082"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413972"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref23","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3003779"},{"key":"ref27","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12230"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00139"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2812605"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12281"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11770"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2612829"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2864920"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"ref39","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref42","first-page":"1","article-title":"How much position information do convolutional neural networks encode?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Islam"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09733172.pdf?arnumber=9733172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:55:10Z","timestamp":1705535710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9733172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3148867","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}