{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:25Z","timestamp":1777865485112,"version":"3.51.4"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01337","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14409-14419","source":"Crossref","is-referenced-by-count":0,"title":["SAMPLE: Semantic Alignment through Temporal-Adaptive Multimodal Prompt Learning for Event-Based Open-Vocabulary Action Recognition"],"prefix":"10.1109","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqin","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingtao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiejun","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Ez-clip: Efficient zeroshot video action recognition","author":"Ahmad","year":"2023","journal-title":"arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.781"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.781"},{"key":"ref4","first-page":"C186","article-title":"A $240 \\times 18010 \\text{mw} 12 \\text{us}$ latency sparse-output vision sensor for mobile applications","volume-title":"Symposium on VLSI Circuits","author":"Berner"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341740"},{"key":"ref7","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3008413"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3300741"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/189"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-024-03721-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","article-title":"Froster: Frozen clip is a strong teacher for open-vocabulary action recognition","author":"Huang","year":"2024","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412991"},{"key":"ref18","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia"},{"key":"ref19","article-title":"Embodied neuromorphic vision with event-driven random backpropagation","author":"Kaiser","year":"2019","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00424"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref22","volume-title":"How to adapt your large-scale vision-and-language model","author":"Kim","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611758"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611759"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394551"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3574499"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/240"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/240"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00275"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00038"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01931"},{"key":"ref38","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00301"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01205"},{"key":"ref42","article-title":"Slayer: Spike layer error reassignment in time","volume":"31","author":"Shrestha","year":"2018","journal-title":"NeurIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref45","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28361"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28372"},{"key":"ref48","article-title":"Sstformer: bridging spiking neural network and memory support transformer for frameevent based recognition","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00169"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2019.2945630"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140819"},{"key":"ref54","article-title":"Tip-adapter: Training-free clip-adapter for better visionlanguage modeling","author":"Zhang","year":"2022","journal-title":"ECCV"},{"key":"ref55","article-title":"Image fusion via vision-language model","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Zhao"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01763"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref59","article-title":"Spikformer: When spiking neural network meets transformer","author":"Zhou","year":"2022","journal-title":"arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444118.pdf?arnumber=11444118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:40:37Z","timestamp":1777531237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01337","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}