{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T18:39:03Z","timestamp":1792521543048,"version":"4.5.0"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109583","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T23:05:40Z","timestamp":1788390340000},"page":"109583","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["SynNeura: Event-driven liquid-spiking dynamics for weakly supervised multimodal temporal alignment"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3665-028X","authenticated-orcid":false,"given":"Yuping","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109583_bib0001","series-title":"Proceedings of the IEEE international conference on computer vision (ICCV)","first-page":"609","article-title":"Look, listen and learn","author":"Arandjelovi\u0107","year":"2017"},{"key":"10.1016\/j.neunet.2026.109583_bib0002","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"1708","article-title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","author":"Bain","year":"2021"},{"issue":"2","key":"10.1016\/j.neunet.2026.109583_bib0003","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"10.1016\/j.neunet.2026.109583_bib0004","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-025-02670-6","article-title":"Learning robust event-guided representations for person re-identification","volume":"134","author":"Cao","year":"2026","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109583_bib0005","article-title":"Event-driven video restoration with spiking-convolutional architecture","volume":"1\u201315","author":"Cao","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109583_bib0006","series-title":"Advances in neural information processing systems (neurIPS)","first-page":"6571","article-title":"Neural ordinary differential equations","volume":"vol. 31","author":"Chen","year":"2018"},{"key":"10.1016\/j.neunet.2026.109583_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"3444","article-title":"Lip reading sentences in the wild","author":"Chung","year":"2017"},{"key":"10.1016\/j.neunet.2026.109583_bib0008","series-title":"Proceedings of the international conference on machine learning (ICML)","first-page":"894","article-title":"Soft-DTW: A differentiable loss function for time-series","author":"Cuturi","year":"2017"},{"issue":"1","key":"10.1016\/j.neunet.2026.109583_bib0009","first-page":"5199","article-title":"Comprehensive SNN learning with differentiable spike timing","volume":"13","author":"Deng","year":"2022","journal-title":"Nature Communications"},{"key":"10.1016\/j.neunet.2026.109583_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"1801","article-title":"Temporal cycle-consistency learning","author":"Dwibedi","year":"2019"},{"key":"10.1016\/j.neunet.2026.109583_bib0011","series-title":"Proceedings of the international conference on learning representations (ICLR)","article-title":"Large scale sequence modeling with hierarchical recurrent networks","author":"Elsayed","year":"2019"},{"issue":"40","key":"10.1016\/j.neunet.2026.109583_bib0012","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adi1480","article-title":"Spikingjelly: An open-source machine learning infrastructure platform for spike-based intelligence","volume":"9","author":"Fang","year":"2023","journal-title":"Science Advances"},{"key":"10.1016\/j.neunet.2026.109583_bib0013","series-title":"Advances in neural information processing systems (neurIPS)","first-page":"21056","article-title":"Deep residual learning in spiking neural networks","volume":"vol. 34","author":"Fang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109583_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"2448","article-title":"You can ground earlier than see: An effective and efficient pipeline for temporal sentence grounding in compressed videos","author":"Fang","year":"2023"},{"issue":"12","key":"10.1016\/j.neunet.2026.109583_bib0015","doi-asserted-by":"crossref","first-page":"5841","DOI":"10.1007\/s11263-024-02148-x","article-title":"Event-driven heterogeneous network for video deraining","volume":"132","author":"Fu","year":"2024","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"10.1016\/j.neunet.2026.109583_bib0016","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","article-title":"Event-based vision: A survey","volume":"44","author":"Gallego","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109583_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"13884","article-title":"Recurrent vision transformers for object detection with event cameras","author":"Gehrig","year":"2023"},{"key":"10.1016\/j.neunet.2026.109583_bib0018","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7657","article-title":"Liquid time-constant networks","volume":"vol. 35","author":"Hasani","year":"2021"},{"issue":"11","key":"10.1016\/j.neunet.2026.109583_bib0019","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1038\/s42256-022-00556-7","article-title":"Closed-form continuous-time neural networks","volume":"4","author":"Hasani","year":"2022","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109583_bib0020","series-title":"Proceedings of the IEEE international conference on computer vision (ICCV)","first-page":"5803","article-title":"Localizing moments in video with natural language","author":"Hendricks","year":"2017"},{"key":"10.1016\/j.neunet.2026.109583_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110776","article-title":"Weakly supervised content-based video moment retrieval using low-rank video representation","volume":"277","author":"Huo","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109583_bib0022","series-title":"Advances in neural information processing systems(neurIPS)","first-page":"6696","article-title":"Neural controlled differential equations for irregular time series","volume":"vol. 33","author":"Kidger","year":"2020"},{"issue":"10","key":"10.1016\/j.neunet.2026.109583_bib0023","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1038\/s42256-020-00237-3","article-title":"Neural circuit policies enabling auditable autonomy","volume":"2","author":"Lechner","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109583_bib0024","series-title":"Advances in neural information processing systems (NeurIPS)","first-page":"11846","article-title":"QVHighlights: Detecting moments and highlights in videos via natural language queries","volume":"vol. 34","author":"Lei","year":"2021"},{"issue":"4","key":"10.1016\/j.neunet.2026.109583_bib0025","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"International Journal of Forecasting"},{"key":"10.1016\/j.neunet.2026.109583_bib0026","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"2794","article-title":"UniVTG: Towards unified video-language temporal grounding","author":"Lin","year":"2023"},{"key":"10.1016\/j.neunet.2026.109583_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113200","article-title":"Weakly supervised spatial-temporal video grounding via spatial-temporal annotation on a single frame","volume":"314","author":"Luo","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109583_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"9879","article-title":"End-to-end learning of visual representations from uncurated instructional videos","author":"Miech","year":"2020"},{"key":"10.1016\/j.neunet.2026.109583_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"12475","article-title":"Audio-visual instance discrimination with cross-modal agreement","author":"Morgado","year":"2021"},{"key":"10.1016\/j.neunet.2026.109583_bib0030","series-title":"Proceedings of the international conference on machine learning (ICML)","first-page":"7829","article-title":"Neural rough differential equations for long time series","author":"Morrill","year":"2021"},{"key":"10.1016\/j.neunet.2026.109583_bib0031","series-title":"Proceedings of the international conference on machine learning (ICML)","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"7784","key":"10.1016\/j.neunet.2026.109583_bib0032","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.109583_bib0033","series-title":"Advances in neural information processing systems","first-page":"5321","article-title":"Latent ordinary differential equations for irregularly-sampled time series","volume":"vol. 32","author":"Rubanova","year":"2019"},{"key":"10.1016\/j.neunet.2026.109583_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"5610","article-title":"Spikingresformer: Bridging resnet and vision transformer in spiking neural networks","author":"Shi","year":"2024"},{"key":"10.1016\/j.neunet.2026.109583_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"1233","article-title":"Human action recognition with multimodal features","author":"Song","year":"2013"},{"key":"10.1016\/j.neunet.2026.109583_bib0036","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","article-title":"Deep learning in spiking neural networks","volume":"111","author":"Tavanaei","year":"2019","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109583_bib0037","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"Tian","year":"2018"},{"key":"10.1016\/j.neunet.2026.109583_bib0038","series-title":"Proceedings of the annual meeting of the association for computational linguistics (ACL)","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","author":"Tsai","year":"2020"},{"key":"10.1016\/j.neunet.2026.109583_bib0039","series-title":"Proceedings of the annual meeting of the association for computational linguistics (ACL)","first-page":"1387","article-title":"Ms-detr: Natural language video localization with sampling moment-moment interaction","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109583_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"636","article-title":"Protege: Untrimmed pretraining for video temporal grounding by video temporal grounding","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109583_bib0041","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"1761","article-title":"Masked spiking transformer","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109583_bib0042","series-title":"Advances in neural information processing systems(neurIPS)","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"vol. 34","author":"Wu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109583_bib0043","series-title":"Proceedings of the conference on empirical methods in natural language processing (EMNLP)","first-page":"6787","article-title":"VideoCLIP: Contrastive pre-training for zero-shot video-text understanding","author":"Xu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109583_bib0044","series-title":"Proceedings of the conference on empirical methods in natural language processing (EMNLP)","first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.neunet.2026.109583_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110193","article-title":"Bio-inspired active learning method in spiking neural network","volume":"261","author":"Zhan","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109583_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106744","article-title":"Center-enhanced video captioning model with multimodal semantic alignment","volume":"180","author":"Zhang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109583_bib0047","series-title":"Proceedings of the international ACM SIGIR conference on research and development in information retrieval (SIGIR)","first-page":"685","article-title":"Video corpus moment retrieval with contrastive learning","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109583_bib0048","series-title":"Proceedings of the annual meeting of the association for computational linguistics (ACL)","first-page":"6543","article-title":"Span-based localizing network for natural language video localization","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109583_bib0049","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12870","article-title":"Learning 2d temporal adjacent networks for moment localization with natural language","volume":"vol. 34","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109583_bib0050","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7590","article-title":"Towards automatic learning of procedures from web instructional videos","volume":"vol. 32","author":"Zhou","year":"2018"},{"key":"10.1016\/j.neunet.2026.109583_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112592","article-title":"Query-aware multi-scale proposal network for weakly supervised temporal sentence grounding in videos","volume":"304","author":"Zhou","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109583_bib0052","series-title":"Proceedings of the international conference on learning representations (ICLR)","article-title":"Spikformer: When spiking neural network meets transformer","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neunet.2026.109583_bib0053","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"5819","article-title":"State space models for event cameras","author":"Zubi\u0107","year":"2024"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026010403?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026010403?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T17:45:50Z","timestamp":1792518350000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026010403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":53,"alternative-id":["S0893608026010403"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109583","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SynNeura: Event-driven liquid-spiking dynamics for weakly supervised multimodal temporal alignment","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109583","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109583"}}