{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T21:28:45Z","timestamp":1772141325185,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["91748122"],"award-info":[{"award-number":["91748122"]}],"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":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3497997","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T13:43:24Z","timestamp":1731591804000},"page":"2768-2781","source":"Crossref","is-referenced-by-count":2,"title":["Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5515-1943","authenticated-orcid":false,"given":"Yeming","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0001-0204","authenticated-orcid":false,"given":"Siyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6052-2781","authenticated-orcid":false,"given":"Yaoru","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2124-0869","authenticated-orcid":false,"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5868-8854","authenticated-orcid":false,"given":"Weijian","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4622-0119","authenticated-orcid":false,"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2034"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref10","first-page":"23818","article-title":"Efficient training of visual transformers with small datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref12","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref15","first-page":"642","article-title":"UniLMv2: Pseudo-masked language models for unified language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6787"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/347"},{"key":"ref19","article-title":"Spiking GATs: Learning graph attentions via spiking neural network","author":"Wang","year":"2022","journal-title":"arXiv:2209.13539"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/338"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00860"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3327081"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref30","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Gan"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref32","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref34","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref35","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020","journal-title":"arXiv:2004.00849"},{"key":"ref36","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv:2107.06383"},{"key":"ref37","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00435"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107447615"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ac8828"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17320"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref45","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv:1609.08144"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref47","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref51","article-title":"Visual entailment task for visually-grounded language learning","author":"Xie","year":"2018","journal-title":"arXiv:1811.10582"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350925"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref54","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02226"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462981"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"ref61","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"Zeng","year":"2021","journal-title":"arXiv:2111.08276"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref65","first-page":"5696","article-title":"OmniVL: One foundation model for image-language and video-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00119"},{"key":"ref67","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref68","first-page":"1","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref69","article-title":"Prompt tuning for generative multimodal pretrained models","author":"Yang","year":"2022","journal-title":"arXiv:2208.02532"},{"key":"ref70","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00266"},{"key":"ref72","article-title":"Optimal ANN-SNN conversion for high-accuracy and ultra-low-latency spiking neural networks","author":"Bu","year":"2023","journal-title":"arXiv:2303.04347"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10753025.pdf?arnumber=10753025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:46:39Z","timestamp":1772138799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10753025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":72,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3497997","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}