{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:28:52Z","timestamp":1770917332887,"version":"3.50.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["U19A2057"],"award-info":[{"award-number":["U19A2057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-037"],"award-info":[{"award-number":["GXXT-2022-037"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2023.3343520","type":"journal-article","created":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T19:58:55Z","timestamp":1702670335000},"page":"5266-5281","source":"Crossref","is-referenced-by-count":14,"title":["Cascade Semantic Prompt Alignment Network for Image Captioning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9561-7550","authenticated-orcid":false,"given":"Jingyu","family":"Li","sequence":"first","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-2546","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"given":"Bo","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/91"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475607"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19940"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3268066"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref19","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage HOI detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/224"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref24","article-title":"Adaptively clustering neighbor elements for image captioning","author":"Wang","year":"2023","journal-title":"arXiv:2301.01955"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref26","article-title":"Compact bidirectional transformer for image captioning","author":"Zhou","year":"2022","journal-title":"arXiv:2201.01984"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2965966"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063297"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414004"},{"key":"ref34","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref35","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref36","article-title":"Patch-token aligned Bayesian prompt learning for vision-language models","author":"Liu","year":"2023","journal-title":"arXiv:2303.09100"},{"key":"ref37","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref40","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv:2208.01626"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_4"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00867"},{"key":"ref44","article-title":"DeCap: Decoding CLIP latents for zero-shot captioning via text-only training","author":"Li","year":"2023","journal-title":"arXiv:2303.03032"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3472810"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref50","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Herdade"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548409"},{"key":"ref57","article-title":"OSIC: A new one-stage image captioner coined","author":"Wang","year":"2022","journal-title":"arXiv:2211.02321"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"issue":"6","key":"ref61","first-page":"1111","article-title":"Review of omnimedia content quality evaluation","volume":"38","author":"Yan","year":"2022","journal-title":"J. Signal Process."},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3468872"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref65","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref73","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"Zeng","year":"2021","journal-title":"arXiv:2111.08276"},{"key":"ref74","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv:2108.10904"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref76","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref77","article-title":"PALI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022","journal-title":"arXiv:2209.06794"},{"key":"ref78","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25137"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3243725"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/151"},{"key":"ref85","article-title":"ClipCap: Clip prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref86","article-title":"How much can clip benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv:2107.06383"},{"key":"ref87","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.266"},{"key":"ref89","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"issue":"11","key":"ref90","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10360871.pdf?arnumber=10360871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:12:49Z","timestamp":1736453569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10360871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":90,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3343520","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}