{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:22:00Z","timestamp":1781929320062,"version":"3.54.5"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62225208"],"award-info":[{"award-number":["62225208"]}],"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":["61906007"],"award-info":[{"award-number":["61906007"]}],"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":["62276010"],"award-info":[{"award-number":["62276010"]}],"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":["62306253"],"award-info":[{"award-number":["62306253"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Guangdong Natural Science Fund-General Program","doi-asserted-by":"publisher","award":["2024A1515010233"],"award-info":[{"award-number":["2024A1515010233"]}],"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":[[2025]]},"DOI":"10.1109\/tip.2025.3528216","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:47:06Z","timestamp":1737053226000},"page":"594-607","source":"Crossref","is-referenced-by-count":7,"title":["Intra- and Inter-Head Orthogonal Attention for Image Captioning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7002-5447","authenticated-orcid":false,"given":"Xiaodan","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9019-4087","authenticated-orcid":false,"given":"Aozhe","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Computer Science, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-741X","authenticated-orcid":false,"given":"Junzhong","family":"Ji","sequence":"additional","affiliation":[{"name":"College of Computer Science, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8235-7852","authenticated-orcid":false,"given":"Liangqiong","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computing and Data Science, The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-3833-5_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref10","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref14","first-page":"14014","article-title":"Are sixteen heads really better than one?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Michel"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1317"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1359"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.260"},{"key":"ref19","first-page":"4266","article-title":"Can we gain more from orthogonality regularizations in training deep networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bansal"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004729"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612245"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169061"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01749"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref32","article-title":"Leveraging redundancy in attention with reuse transformers","author":"Bhojanapalli","year":"2021","journal-title":"arXiv:2110.06821"},{"key":"ref33","first-page":"3570","article-title":"On orthogonality and learning recurrent networks with long term dependencies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Vorontsov"},{"key":"ref34","first-page":"2401","article-title":"Efficient orthogonal parametrisation of recurrent neural networks using householder reflections","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mhammedi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01152"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2948352"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3171297"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.48"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3155795"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185320"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28178"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3353830"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL","author":"Banerjee"},{"key":"ref53","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref56","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref60","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref62","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Li"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242142"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328298"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_42"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.408"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107650"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.965"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10844064.pdf?arnumber=10844064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T19:17:12Z","timestamp":1738178232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10844064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3528216","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}