{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T12:48:10Z","timestamp":1763038090480,"version":"build-2065373602"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["2023YFB4301800"],"award-info":[{"award-number":["2023YFB4301800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Shaanxi Province General Program Project","award":["2025JC-YBMS-673"],"award-info":[{"award-number":["2025JC-YBMS-673"]}]},{"name":"New Generation Information Technology Innovation Project","award":["2023IT080"],"award-info":[{"award-number":["2023IT080"]}]},{"DOI":"10.13039\/501100012226","name":"Basic Scientific Research Funds of Central Universities","doi-asserted-by":"publisher","award":["300102404101"],"award-info":[{"award-number":["300102404101"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3577292","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T13:39:49Z","timestamp":1750340389000},"page":"18792-18804","source":"Crossref","is-referenced-by-count":1,"title":["SFAN: Selective Filter and Alignment Network for Cross-Modal Retrieval"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6462-6087","authenticated-orcid":false,"given":"Yongle","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0345-804X","authenticated-orcid":false,"given":"Zedong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4043-8448","authenticated-orcid":false,"given":"Shijie","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang’an University, Xi’an, Shaanxi, WA, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1940-625X","authenticated-orcid":false,"given":"Ningning","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang’an University, Xi’an, Shaanxi, WA, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9059-330X","authenticated-orcid":false,"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Business and Law, Edith Cowan University, Joondalup, WA, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2016.08.012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111457"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446571"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref6","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref8","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413877"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Faghri","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892802"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463031"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3214208"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325043"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612427"},{"key":"ref30","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"ref32","first-page":"1","article-title":"Long range language modeling via gated state spaces","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mehta"},{"key":"ref33","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref34","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref35","article-title":"LocalMamba: Visual state space model with windowed selective scan","author":"Huang","year":"2024","journal-title":"arXiv:2403.09338"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3261443"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348297"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01637"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3429192"},{"key":"ref43","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref44","article-title":"PointMamba: A simple state space model for point cloud analysis","author":"Liang","year":"2024","journal-title":"arXiv:2402.10739"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref48","first-page":"1","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref50","first-page":"12381","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3276796"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3188569"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611703"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103716"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref57","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"ref62","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref64","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv:2210.07225"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11045177.pdf?arnumber=11045177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:49Z","timestamp":1759945129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":65,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3577292","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}