{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T21:14:49Z","timestamp":1783372489729,"version":"3.54.6"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134425","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:27:01Z","timestamp":1783034821000},"page":"134425","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CLIP-based dual temporal decoupling network for video action recognition"],"prefix":"10.1016","volume":"699","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5570-2395","authenticated-orcid":false,"given":"Yinbin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5783-8133","authenticated-orcid":false,"given":"Jing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JianPing","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134425_bib0005","article-title":"T2L: efficient zero-shot action recognition with temporal token learning","volume":"2025","author":"Ahmad","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134425_bib0010","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6836","article-title":"Vivit: a video vision transformer","author":"Arnab","year":"2021"},{"key":"10.1016\/j.neucom.2026.134425_bib0015","series-title":"ICML","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.neucom.2026.134425_bib0020","author":"Bosetti"},{"key":"10.1016\/j.neucom.2026.134425_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4613","article-title":"Rethinking zero-shot video classification: end-to-end training for realistic applications","author":"Brattoli","year":"2020"},{"key":"10.1016\/j.neucom.2026.134425_bib0030","doi-asserted-by":"crossref","first-page":"16664","DOI":"10.52202\/068431-1212","article-title":"Adaptformer: adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134425_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"13638","article-title":"Elaborative rehearsal for zero-shot action recognition","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.134425_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11583","article-title":"Decoupling zero-shot semantic segmentation","author":"Ding","year":"2022"},{"key":"10.1016\/j.neucom.2026.134425_bib0045","series-title":"International Conference on Learning Representations","first-page":"1","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neucom.2026.134425_bib0050","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8303","article-title":"I know the relationships: zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs","author":"Gao","year":"2019"},{"key":"10.1016\/j.neucom.2026.134425_bib0055","series-title":"Asian Conference on Computer Vision","first-page":"4577","article-title":"Telling stories for common sense zero-shot action recognition","author":"Gowda","year":"2024"},{"key":"10.1016\/j.neucom.2026.134425_bib0060","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"5842","article-title":"The \u201csomething something\u201d video database for learning and evaluating visual common sense","author":"Goyal","year":"2017"},{"key":"10.1016\/j.neucom.2026.134425_bib0065","author":"Gu"},{"key":"10.1016\/j.neucom.2026.134425_bib0070","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.neucom.2026.134425_bib0075","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1501","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","author":"Huang","year":"2017"},{"key":"10.1016\/j.neucom.2026.134425_bib0080","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neucom.2026.134425_bib0085","author":"Jia"},{"key":"10.1016\/j.neucom.2026.134425_bib0090","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3143","article-title":"Style normalization and restitution for generalizable person re-identification","author":"Jin","year":"2020"},{"key":"10.1016\/j.neucom.2026.134425_bib0095","series-title":"European Conference on Computer Vision","first-page":"105","article-title":"Prompting visual-language models for efficient video understanding","author":"Ju","year":"2022"},{"key":"10.1016\/j.neucom.2026.134425_bib0100","series-title":"2011 International Conference on Computer Vision","first-page":"2556","article-title":"HMDB: a large video database for human motion recognition","author":"Kuehne","year":"2011"},{"key":"10.1016\/j.neucom.2026.134425_bib0105","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.eswa.2024.124786","article-title":"ESC-ZSAR: expanded semantics from categories with cross-attention for zero-shot action recognition","volume":"255","author":"Lee","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134425_bib0110","author":"Li"},{"key":"10.1016\/j.neucom.2026.134425_bib0115","series-title":"European Conference on Computer Vision","first-page":"388","article-title":"Frozen clip models are efficient video learners","author":"Lin","year":"2022"},{"key":"10.1016\/j.neucom.2026.134425_bib0120","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134425_bib0125","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6555","article-title":"Revisiting temporal modeling for clip-based image-to-video knowledge transferring","author":"Liu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134425_bib0130","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3202","article-title":"Video swin transformer","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134425_bib0135","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Expanding language-image pretrained models for general video recognition","author":"Ni","year":"2022"},{"key":"10.1016\/j.neucom.2026.134425_bib0140","doi-asserted-by":"crossref","first-page":"26462","DOI":"10.52202\/068431-1919","article-title":"St-adapter: parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134425_bib0145","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"464","article-title":"Two at once: enhancing learning and generalization capacities via ibn-net","author":"Pan","year":"2018"},{"key":"10.1016\/j.neucom.2026.134425_bib0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111402","article-title":"Semantic matters: a constrained approach for zero-shot video action recognition","volume":"162","author":"Quan","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134425_bib0155","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134425_bib0160","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6545","article-title":"Fine-tuned clip models are efficient video learners","author":"Rasheed","year":"2023"},{"key":"10.1016\/j.neucom.2026.134425_bib0165","author":"Soomro"},{"key":"10.1016\/j.neucom.2026.134425_bib0170","doi-asserted-by":"crossref","first-page":"10078","DOI":"10.52202\/068431-0732","article-title":"Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134425_bib0175","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2015"},{"key":"10.1016\/j.neucom.2026.134425_bib0180","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6450","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"Tran","year":"2018"},{"key":"10.1016\/j.neucom.2026.134425_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111770","article-title":"VLPA-CLIP: video language prompting and adapting CLIP for efficient video action recognition","volume":"168","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134425_bib0190","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5517","article-title":"A multimodal, multi-task adapting framework for video action recognition","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134425_bib0195","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134425_bib0200","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23034","article-title":"Vita-clip: video and text adaptive clip via multimodal prompting","author":"Wasim","year":"2023"},{"key":"10.1016\/j.neucom.2026.134425_bib0205","series-title":"International Conference on Machine Learning","first-page":"36978","article-title":"Open-vclip: transforming clip to an open-vocabulary video model via interpolated weight optimization","author":"Weng","year":"2023"},{"key":"10.1016\/j.neucom.2026.134425_bib0210","author":"Wu"},{"key":"10.1016\/j.neucom.2026.134425_bib0215","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification","author":"Xie","year":"2018"},{"key":"10.1016\/j.neucom.2026.134425_bib0220","article-title":"Unbiased spatial-temporal atomic fusion-based zero-shot action recognition","author":"Xing","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134425_bib0225","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18816","article-title":"Svformer: semi-supervised video transformer for action recognition","author":"Xing","year":"2023"},{"key":"10.1016\/j.neucom.2026.134425_bib0230","author":"Xu"},{"key":"10.1016\/j.neucom.2026.134425_bib0235","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"23826","article-title":"MMA: multi-modal adapter for vision-language models","author":"Yang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134425_bib0240","author":"Yang"},{"key":"10.1016\/j.neucom.2026.134425_bib0245","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/TCSVT.2024.3390133","article-title":"GBC: guided alignment and adaptive boosting CLIP bridging vision and language for robust action recognition","volume":"34","author":"Yang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134425_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124183","article-title":"Epk-clip: external and priori knowledge clip for action recognition","volume":"252","author":"Yang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134425_bib0255","author":"Yuan"},{"key":"10.1016\/j.neucom.2026.134425_bib0260","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134425_bib0265","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8552","article-title":"Pointclip: point cloud understanding by clip","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134425_bib0270","series-title":"European Conference on Computer Vision (ECCV)","first-page":"696","article-title":"DenseCLIP: extract free dense labels from CLIP","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neucom.2026.134425_bib0275","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018230?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018230?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T20:24:18Z","timestamp":1783369458000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226018230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":55,"alternative-id":["S0925231226018230"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134425","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CLIP-based dual temporal decoupling network for video action recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134425","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134425"}}