{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:03:41Z","timestamp":1773824621179,"version":"3.50.1"},"reference-count":59,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076030"],"award-info":[{"award-number":["62076030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation of China","award":["L201023"],"award-info":[{"award-number":["L201023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3215861","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:39:20Z","timestamp":1667511560000},"page":"6904-6916","source":"Crossref","is-referenced-by-count":10,"title":["TSFNet: Triple-Steam Image Captioning"],"prefix":"10.1109","volume":"25","author":[{"given":"Nannan","family":"Hu","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7105-4207","authenticated-orcid":false,"given":"Yue","family":"Ming","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxiao","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7959-2472","authenticated-orcid":false,"given":"Fan","family":"Feng","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01249"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3093725"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-1338-8_43"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3177745"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119754"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16423"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00435"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00144"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3042192"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref22","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548409"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103068"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref26","first-page":"2085","article-title":"Phrase-based image captioning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lebret","year":"2015"},{"key":"ref27","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ordonez","year":"2011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350996"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2954750"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018957"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060948"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref41","first-page":"361","article-title":"Multimodal residual learning for visual QA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.664"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3460474"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref56","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref58","first-page":"957","article-title":"From word embeddings to document distances","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kusner","year":"2015"},{"key":"ref59","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09925072.pdf?arnumber=9925072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:15:31Z","timestamp":1705961731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9925072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3215861","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}