{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T11:50:44Z","timestamp":1772884244664,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF0900500"],"award-info":[{"award-number":["2021YFF0900500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2035"],"award-info":[{"award-number":["U22B2035"]}],"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":["61972115"],"award-info":[{"award-number":["61972115"]}],"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":["12271083"],"award-info":[{"award-number":["12271083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tcsvt.2022.3233042","type":"journal-article","created":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T18:42:38Z","timestamp":1672339358000},"page":"3516-3528","source":"Crossref","is-referenced-by-count":33,"title":["Neuron-Based Spiking Transmission and Reasoning Network for Robust Image-Text Retrieval"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2393-9016","authenticated-orcid":false,"given":"Wenrui","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}]},{"given":"Zhengyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3178-9772","authenticated-orcid":false,"given":"Liang-Jian","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747440"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref52","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3017344"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186714"},{"key":"ref54","first-page":"1","article-title":"Im2Text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc NeuIPS"},{"key":"ref17","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HIT"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref19","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc ICML"},{"key":"ref18","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeuIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3407197.3407211"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.12.038"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727213"},{"key":"ref48","article-title":"Deep spiking networks","author":"o\u2019connor","year":"2016","journal-title":"arXiv 1602 08323"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00934"},{"key":"ref42","article-title":"An empirical study of training end-to-end vision-and-language transformers","author":"dou","year":"2021","journal-title":"arXiv 2111 02387"},{"key":"ref41","first-page":"1","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","author":"xue","year":"2021","journal-title":"Proc NeuIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596934"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref7","first-page":"2121","article-title":"A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc NeuIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182549"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref6","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc BMVC"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3396520"},{"key":"ref40","first-page":"1","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"Proc ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref36","first-page":"104","article-title":"UNITER: Universal image-text representation learning","author":"chen","year":"2020","journal-title":"Proc ECCV"},{"key":"ref31","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc NeuIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878899"},{"key":"ref39","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"2020","journal-title":"arXiv 2004 00849"},{"key":"ref38","article-title":"WenLan: Bridging vision and language by large-scale multi-modal pre-training","author":"huo","year":"2021","journal-title":"arXiv 2103 06561"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2019.8815416"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref26","first-page":"1","article-title":"Neural joint source-channel coding","author":"choi","year":"2019","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2987203"},{"key":"ref20","first-page":"1","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"jia","year":"2021","journal-title":"Proc ICML"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135420"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/584091.584093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref27","first-page":"1","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"zeng","year":"2022","journal-title":"Proc ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462838"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17034"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10170754\/10003241.pdf?arnumber=10003241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:57:07Z","timestamp":1689616627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10003241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":63,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3233042","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}