{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T20:07:15Z","timestamp":1779739635326,"version":"3.53.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Intergovernmental International Scientific and Technological Innovation Cooperation Project of the National Key Research and Development Program","award":["2025YFE0199900"],"award-info":[{"award-number":["2025YFE0199900"]}]},{"name":"Guangdong Technology","award":["2023TX07Z126"],"award-info":[{"award-number":["2023TX07Z126"]}]},{"name":"CAS Key Technology Talent Program"},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011754"],"award-info":[{"award-number":["2024A1515011754"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan Science and Technology","award":["202305AF150152"],"award-info":[{"award-number":["202305AF150152"]}]},{"name":"Yunnan Science and Technology","award":["202302AD080008"],"award-info":[{"award-number":["202302AD080008"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376261"],"award-info":[{"award-number":["62376261"]}],"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":["62372440"],"award-info":[{"award-number":["62372440"]}],"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":["U21A20487"],"award-info":[{"award-number":["U21A20487"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Technology Project","award":["JCYJ20240813154723031"],"award-info":[{"award-number":["JCYJ20240813154723031"]}]},{"name":"Shenzhen Technology Project","award":["JCYJ20220818101206014"],"award-info":[{"award-number":["JCYJ20220818101206014"]}]},{"name":"Shenzhen Technology Project","award":["JCYJ20220818101206014"],"award-info":[{"award-number":["JCYJ20220818101206014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3654377","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:50:42Z","timestamp":1768510242000},"page":"3667-3681","source":"Crossref","is-referenced-by-count":0,"title":["Language-Guided Multimodal Spiking Neural Networks for Event-Based Action Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7940-294X","authenticated-orcid":false,"given":"Ziliang","family":"Ren","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Dongguan University of Technology, Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5139-6488","authenticated-orcid":false,"given":"Jiaqi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dongguan University of Technology, Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-4486","authenticated-orcid":false,"given":"Fuxiang","family":"Wu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6358-1840","authenticated-orcid":false,"given":"Qieshi","family":"Zhang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3131-3275","authenticated-orcid":false,"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380255"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3302471"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076165"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3318601"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3428316"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260638"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3607771"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28372"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3368964"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00038"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/240"},{"key":"ref15","first-page":"1","article-title":"SpikePoint: An efficient point-based spiking neural network for event cameras action recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2024"},{"key":"ref16","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01763"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369863"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00199"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32207"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref24","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.781"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0093"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023597"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612258"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3300741"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.07.008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01821"},{"key":"ref33","first-page":"1","article-title":"Spike-driven transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yao","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00555"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00536"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2025.3568833"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00943"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387690"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27817"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/180"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0617"},{"key":"ref42","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_27"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00266"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1677-2"},{"key":"ref47","first-page":"3133","article-title":"TIM: An efficient temporal interaction module for spiking transformer","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Shen","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i3.37207"},{"key":"ref49","first-page":"1","article-title":"SpikFormer: When spiking neural network meets transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3208740"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28975"},{"key":"ref52","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3377717"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adi1480"},{"key":"ref55","first-page":"1","article-title":"ST-EVNet: Hierarchical spatial and temporal feature learning on space-time event clouds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3556561"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945630"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/189"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140819"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5486"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3177744"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412991"},{"key":"ref66","first-page":"21056","article-title":"Deep residual learning in spiking neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fang","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202659"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11353471.pdf?arnumber=11353471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:55:16Z","timestamp":1779738916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3654377","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}