{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T16:33:45Z","timestamp":1782750825372,"version":"3.54.5"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFA1008500"],"award-info":[{"award-number":["2023YFA1008500"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["624B2049"],"award-info":[{"award-number":["624B2049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62027804"],"award-info":[{"award-number":["62027804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62332002"],"award-info":[{"award-number":["62332002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402138"],"award-info":[{"award-number":["62402138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["HIT.DZJJ.2024025"],"award-info":[{"award-number":["HIT.DZJJ.2024025"]}],"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":[[2025,11]]},"DOI":"10.1109\/tcsvt.2025.3574499","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T14:12:26Z","timestamp":1748441546000},"page":"10772-10786","source":"Crossref","is-referenced-by-count":7,"title":["Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning"],"prefix":"10.1109","volume":"35","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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5401-5676","authenticated-orcid":false,"given":"Penghong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5763-2493","authenticated-orcid":false,"given":"Xingtao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of AI for Science and the Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00095"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_28"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17215"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3430080"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611759"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00450"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486344"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326694"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337134"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318220"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800793"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00398"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2963386"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460541"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187826"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3248483"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3036667"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00502"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SIMPAR.2016.7862386"},{"key":"ref36","first-page":"969","article-title":"ESIM: An open event camera simulator","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Rebecq"},{"key":"ref37","first-page":"21056","article-title":"Deep residual learning in spiking neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Fang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233042"},{"key":"ref39","article-title":"SpikeMba: Multi-modal spiking saliency mamba for temporal video grounding","author":"Li","year":"2024","journal-title":"arXiv:2404.01174"},{"key":"ref40","article-title":"Spikformer: When spiking neural network meets transformer","author":"Zhou","year":"2022","journal-title":"arXiv:2209.15425"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3114196"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339211"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3368964"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00080"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1302446"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3264836"},{"key":"ref47","first-page":"4660","article-title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Asano"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00508"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref52","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"26","author":"Frome"},{"key":"ref53","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093438"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00724"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref61","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016","journal-title":"arXiv:1609.08675"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11223720\/11016825.pdf?arnumber=11016825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:47:37Z","timestamp":1762195657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11016825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":61,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3574499","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}