{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:56:24Z","timestamp":1777888584399,"version":"3.51.4"},"reference-count":88,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62027804"],"award-info":[{"award-number":["62027804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00810","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8656-8667","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Event Camera Data Pretraining with Adaptive Prompt Fusion"],"prefix":"10.1109","author":[{"given":"Quanmin","family":"Liang","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Li","sequence":"additional","affiliation":[{"name":"Xpeng Motors Technology Co Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinzi","family":"Cao","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyi","family":"Lu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feidiao","family":"Yang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory,Department of Intelligent Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory,Department of Intelligent Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory,Department of Intelligent Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"ref2","author":"Bahng","year":"2022","journal-title":"Exploring visual prompts for adapting largescale models"},{"key":"ref3","author":"Bao","year":"2021","journal-title":"Beit: Bert pre-training of image transformers"},{"key":"ref4","article-title":"Mixmatch: A holistic approach to semi-supervised learning","volume":"32","author":"Berthelot","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref5","author":"Binas","year":"2017","journal-title":"Ddd17: End-to-end davis driving dataset"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2014.2342715"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref10","author":"Chen","year":"2020","journal-title":"Improved baselines with momentum contrastive learning"},{"key":"ref11","author":"Cheng","year":"2020","journal-title":"Structure-aware network for lane marker extraction with dynamic vision sensor"},{"key":"ref12","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"International Conference on Machine Learning","author":"Dehghani","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","author":"Devlin","year":"2018","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref15","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01263"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00407"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3008413"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3224051"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00573"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref26","first-page":"27122721","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"In International conference on machine learning","author":"Hendrycks","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_6"},{"key":"ref28","author":"Huang","year":"2024","journal-title":"Data-efficient event camera pretraining via disentangled masked modeling"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00151"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00215"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00237"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_22"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref37","author":"Liang","journal-title":"Efficient event stream super-resolution with recursive multi-branch fusion"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612462"},{"issue":"2","key":"ref39","first-page":"566576","article-title":"A $128 \\times 128120 \\text{db} 15 \\mu ~\\mathrm{s}$ latency asynchronous temporal contrast vision sensor","author":"Lichtensteiner","year":"2008","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00568"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5194\/isprsannals-II-3-W5-427-2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145053"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917691115"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1106-2"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327605"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2015.00437"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00345"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref54","first-page":"23231","article-title":"Meta-learning to improve pre-training","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00286"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2963386"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-021-00184-y"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00186"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01730"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_20"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28323"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2018.2824899"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01723"},{"key":"ref65","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2793357"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.346"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3220938"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00067"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1046"},{"key":"ref73","author":"Wu","year":"2023","journal-title":"Eventclip: Adapting clip for event-based object recognition"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00982"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_17"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01432"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00989"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01652"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_27"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01763"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.062"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800793"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00108"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00206"}],"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\/11444377.pdf?arnumber=11444377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:52:03Z","timestamp":1777611123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00810","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}