{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:05:42Z","timestamp":1784736342299,"version":"3.55.0"},"reference-count":105,"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\/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"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J01002"],"award-info":[{"award-number":["2021J01002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3164787","type":"journal-article","created":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T19:28:00Z","timestamp":1649186880000},"page":"3723-3736","source":"Crossref","is-referenced-by-count":31,"title":["Knowing What it is: Semantic-Enhanced Dual Attention Transformer"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3423","authenticated-orcid":false,"given":"Yiwei","family":"Ma","sequence":"first","affiliation":[{"name":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[{"name":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, 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":"MediaAnalytics and Computing Laboratory, Department of Artificial Intelligence, 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":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, 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"}]},{"given":"Feiyue","family":"Huang","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":"MediaAnalytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413885"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350996"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3115432"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2915033"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01280"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref25","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi","year":"2020"},{"key":"ref26","first-page":"17427","article-title":"PTR: A benchmark for part-based conceptual, relational, and physical reasoning","volume":"34","author":"Hong","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref27","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref29","article-title":"CPTR: Full transformer network for image captioning","author":"Liu","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413998"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413924"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350993"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350925"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref43","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"31","author":"Yi","year":"2018"},{"key":"ref44","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","author":"Mao","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413760"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413765"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413775"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413499"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413507"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413785"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref56","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref57","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Int. Conf. Mach. Learning. PMLR","author":"Touvron","year":"2021"},{"key":"ref58","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref61","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref62","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref63","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref64","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref70","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nair","year":"2010"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01019"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref78","first-page":"11135","article-title":"Image captioning: Transforming objects into words","author":"Herdade","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref79","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref87","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Banerjee","year":"2005"},{"key":"ref88","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Lin","year":"2004"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref97","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN","author":"Mao","year":"2014"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref104","first-page":"1571","article-title":"Bilinear attentionnetworks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09749944.pdf?arnumber=9749944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:40:45Z","timestamp":1747849245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9749944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3164787","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}