乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:49Z","timestamp":1740132889994,"version":"3.37.3"},"reference-count":66,"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":["62172138","61932009"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2021HGTB0082"],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3154149","type":"journal-article","created":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T20:25:00Z","timestamp":1645734300000},"page":"2966-2977","source":"Crossref","is-referenced-by-count":16,"title":["A Text-Guided Generation and Refinement Model for Image Captioning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6786-0732","authenticated-orcid":false,"given":"Depeng","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data, School of Computer and Information, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1042-8361","authenticated-orcid":false,"given":"Zhenzhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data, School of Computer and Information, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4986-3611","authenticated-orcid":false,"given":"Yuanen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data, School of Computer and Information, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data, School of Computer and Information, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data, School of Computer and Information, Hefei University of Technology, Hefei, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9106007"},{"key":"ref57","first-page":"499","article-title":"Recurrent fusion network for image captioning","author":"jiang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s41809-019-00047-z"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref15","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLR (Poster)"},{"key":"ref14","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref53","article-title":"A package for automatic evaluation of summaries","author":"rouge","year":"0","journal-title":"Proc Workshop Summarizationof ACL"},{"key":"ref52","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proc 43th Annu Meeting Assoc Comput Linguistics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"article-title":"Microsoft COCO captions: Data collection and evaluation server","year":"2015","author":"chen","key":"ref55"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref17","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"0","journal-title":"Proc 13th Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref16","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"0","journal-title":"Proc 15th Conf Comput Nat Lang Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref50","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601784"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206536"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00486"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2075"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1047"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025814"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref35","article-title":"Actor-critic sequence training for image captioning","author":"zhang","year":"2017","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref37","article-title":"A retrieve-and-edit framework for predicting structured outputs","volume":"31","author":"hashimoto","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref36"},{"key":"ref31","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"0","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11237"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0840-y"},{"key":"ref39","first-page":"1","article-title":"Look and modify: Modification networks for image captioning","author":"sammani","year":"2020","journal-title":"Comput Vis Pattern Recognit"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.418"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00350"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"article-title":"Compact bidirectional transformer for image captioning","year":"2022","author":"zhou","key":"ref25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"article-title":"CPTR: Full transformer network for image captioning","year":"2021","author":"liu","key":"ref66"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref65","first-page":"1865","article-title":"Prophet attention: Predicting attention with future attention","volume":"33","author":"liu","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref60","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume":"28","author":"bengio","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref61","article-title":"Image captioning: Transforming objects into words","volume":"32","author":"herdade","year":"2019","journal-title":"Adv Neural Info Process Syst"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09720933.pdf?arnumber=9720933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T17:59:39Z","timestamp":1693245579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9720933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3154149","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2023]]}}}