{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:54:49Z","timestamp":1784904889243,"version":"3.55.0"},"reference-count":93,"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\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037"],"award-info":[{"award-number":["U21B2037"]}],"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":["62176222"],"award-info":[{"award-number":["62176222"]}],"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":["62176223"],"award-info":[{"award-number":["62176223"]}],"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":["62176226"],"award-info":[{"award-number":["62176226"]}],"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":["62072386"],"award-info":[{"award-number":["62072386"]}],"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":["62072387"],"award-info":[{"award-number":["62072387"]}],"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":["62072389"],"award-info":[{"award-number":["62072389"]}],"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":["62002305"],"award-info":[{"award-number":["62002305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019B1515120049"],"award-info":[{"award-number":["2019B1515120049"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province of China","doi-asserted-by":"publisher","award":["2021J01002"],"award-info":[{"award-number":["2021J01002"]}],"id":[{"id":"10.13039\/501100003392","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.2022.3183434","type":"journal-article","created":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T19:41:54Z","timestamp":1655840514000},"page":"4321-4335","source":"Crossref","is-referenced-by-count":43,"title":["Knowing What to Learn: A Metric-Oriented Focal Mechanism for Image Captioning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3423","authenticated-orcid":false,"given":"Yiwei","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5110-4526","authenticated-orcid":false,"given":"Yiyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjian","family":"Wu","sequence":"additional","affiliation":[{"name":"Youtu Laboratory, Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Media Analytics and Computing Laboratory, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3042192"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2824816"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969330"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889922"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004729"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350961"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref34","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref41","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475703"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3116416"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_10"},{"key":"ref47","first-page":"1292","article-title":"Image description using visual dependency representations","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Elliott"},{"key":"ref48","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","volume-title":"Proc. 13th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Mitchell"},{"key":"ref49","article-title":"Exploring nearest neighbor approaches for image captioning","author":"Devlin","year":"2015","journal-title":"arXiv:1505.04467"},{"key":"ref50","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","volume":"2","author":"Karpathy"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/app8050739"},{"key":"ref60","article-title":"Image captioning: Transforming objects into words","author":"Herdade","year":"2019","journal-title":"arXiv:1906.05963"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref64","article-title":"Aligning visual regions and textual concepts for semantic-grounded image representations","author":"Liu","year":"2019","journal-title":"arXiv:1905.06139"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/708"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013470"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref75","article-title":"CLEVRER: CoLlision events for video REpresentation and reasoning","author":"Yi","year":"2019","journal-title":"arXiv:1910.01442"},{"key":"ref76","first-page":"17427","article-title":"PTR: A benchmark for part-based conceptual, relational, and physical reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hong"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_47"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3121705"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_22"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/92"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803418"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref86","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref92","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09802801.pdf?arnumber=9802801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:42:45Z","timestamp":1747849365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9802801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3183434","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}