{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:08:26Z","timestamp":1784203706450,"version":"3.55.0"},"reference-count":62,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61873191"],"award-info":[{"award-number":["61873191"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["7207041147"],"award-info":[{"award-number":["7207041147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973237"],"award-info":[{"award-number":["61973237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2026.134090","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T15:05:55Z","timestamp":1779807955000},"page":"134090","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Enhancing CrossTransformer with fine-grained spatio-temporal modeling for few-shot action recognition"],"prefix":"10.1016","volume":"696","author":[{"given":"Yukai","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0318-8880","authenticated-orcid":false,"given":"Tianyi","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8902-5460","authenticated-orcid":false,"given":"Min","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3752-7749","authenticated-orcid":false,"given":"Gaowei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9947-7746","authenticated-orcid":false,"given":"Yunlong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134090_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127819","article-title":"A dual-prototype network combining query-specific and class-specific attentive learning for few-shot action recognition","volume":"598","author":"Jiang","year":"2024","journal-title":"Neurocomputing"},{"issue":"8","key":"10.1016\/j.neucom.2026.134090_bib0010","doi-asserted-by":"crossref","first-page":"3912","DOI":"10.1109\/TCSVT.2023.3235522","article-title":"AGPN: action granularity pyramid network for video action recognition","volume":"33","author":"Chen","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134090_bib0015","first-page":"1","article-title":"Spatio-temporal decoupled knowledge compensator for few-shot action recognition","author":"Qu","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134090_bib0020","first-page":"1","article-title":"Locality-aware cross-modal correspondence learning for dense audio-visual events detection","author":"Xing","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134090_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127389","article-title":"Action recognition in compressed domains: a survey","volume":"577","author":"Ming","year":"2024","journal-title":"Neurocomputing"},{"issue":"5","key":"10.1016\/j.neucom.2026.134090_bib0030","doi-asserted-by":"crossref","first-page":"3073","DOI":"10.1109\/TCSVT.2021.3100842","article-title":"Dense semantics-assisted networks for video action recognition","volume":"32","author":"Luo","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134090_bib0035","doi-asserted-by":"crossref","first-page":"6593","DOI":"10.1109\/TMM.2025.3586118","article-title":"MVP-shot: multi-velocity progressive-alignment framework for few-shot action recognition","volume":"27","author":"Qu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134090_bib0040","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.neucom.2022.07.046","article-title":"Adaptive spatiotemporal graph convolutional network with intermediate aggregation of multi-stream skeleton features for action recognition","volume":"505","author":"Zhao","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134090_bib0045","series-title":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","first-page":"1372","article-title":"A survey on different computer vision based human activity recognition for surveillance applications","author":"Shenoy","year":"2022"},{"issue":"10","key":"10.1016\/j.neucom.2026.134090_bib0050","doi-asserted-by":"crossref","first-page":"6955","DOI":"10.1109\/TCSVT.2022.3175923","article-title":"Multidimensional prototype refactor enhanced network for few-shot action recognition","volume":"32","author":"Liu","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"10.1016\/j.neucom.2026.134090_bib0055","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1109\/TCSVT.2020.2978855","article-title":"Revisiting hard example for action recognition","volume":"31","author":"Wang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"13s","key":"10.1016\/j.neucom.2026.134090_bib0060","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3582688","article-title":"A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities","volume":"55","author":"Song","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134090_bib0065","first-page":"2734","article-title":"Interventional few-shot learning","volume":"33","author":"Yue","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134090_bib0070","first-page":"21981","article-title":"Crosstransformers: spatially-aware few-shot transfer","volume":"33","author":"Doersch","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134090_bib0075","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9062","article-title":"Meta-baseline: exploring simple meta-learning for few-shot learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.134090_bib0080","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12365","article-title":"Meta-learning of neural architectures for few-shot learning","author":"Elsken","year":"2020"},{"issue":"3","key":"10.1016\/j.neucom.2026.134090_bib0085","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1109\/TCSVT.2020.2995754","article-title":"Multi-scale metric learning for few-shot learning","volume":"31","author":"Jiang","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134090_bib0090","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"751","article-title":"Compound memory networks for few-shot video classification","author":"Zhu","year":"2018"},{"key":"10.1016\/j.neucom.2026.134090_bib0095","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16","first-page":"525","article-title":"Few-shot action recognition with permutation-invariant attention","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134090_bib0100","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"909","article-title":"Tea: temporal excitation and aggregation for action recognition","author":"Li","year":"2020"},{"key":"10.1016\/j.neucom.2026.134090_bib0105","author":"Bishay"},{"key":"10.1016\/j.neucom.2026.134090_bib0110","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 36","first-page":"1404","article-title":"TA2N: two-stage action alignment network for few-shot action recognition","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134090_bib0115","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"475","article-title":"Temporal-relational crosstransformers for few-shot action recognition","author":"Perrett","year":"2021"},{"issue":"4","key":"10.1016\/j.neucom.2026.134090_bib0120","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1109\/TCSVT.2018.2818151","article-title":"Discriminative spatio-temporal pattern discovery for 3D action recognition","volume":"29","author":"Weng","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134090_bib0125","doi-asserted-by":"crossref","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.2026.134090_bib0130","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"4779","article-title":"Fine-grained action recognition with robust motion representation decoupling and concentration","author":"Sun","year":"2022"},{"key":"10.1016\/j.neucom.2026.134090_bib0135","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"Feichtenhofer","year":"2016"},{"key":"10.1016\/j.neucom.2026.134090_bib0140","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2625","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"Donahue","year":"2015"},{"key":"10.1016\/j.neucom.2026.134090_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20030","article-title":"Direcformer: a directed attention in transformer approach to robust action recognition","author":"Truong","year":"2022"},{"issue":"7","key":"10.1016\/j.neucom.2026.134090_bib0150","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3654671","article-title":"Discriminative segment focus network for fine-grained video action recognition","volume":"20","author":"Sun","year":"2024","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.neucom.2026.134090_bib0155","series-title":"ICML, 2","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.neucom.2026.134090_bib0160","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.2026.134090_bib0165","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"5070","article-title":"Exploring coarse-to-fine action token localization and interaction for fine-grained video action recognition","author":"Sun","year":"2023"},{"issue":"1","key":"10.1016\/j.neucom.2026.134090_bib0170","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/TCSVT.2021.3058098","article-title":"Hierarchical graph neural networks for few-shot learning","volume":"32","author":"Chen","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.neucom.2026.134090_bib0175","first-page":"1","article-title":"Generalizing from a few examples: a survey on few-shot learning","volume":"53","author":"Yaqing","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134090_bib0180","author":"Qu"},{"key":"10.1016\/j.neucom.2026.134090_bib0185","series-title":"International Conference on Machine Learning (ICML)","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"10.1016\/j.neucom.2026.134090_bib0190","series-title":"International Conference on Machine Learning (ICML)","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","author":"Santoro","year":"2016"},{"key":"10.1016\/j.neucom.2026.134090_bib0195","series-title":"International Conference on Learning Representations","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2018"},{"key":"10.1016\/j.neucom.2026.134090_bib0200","article-title":"Matching networks for one shot learning","volume":"29","author":"Vinyals","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134090_bib0205","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1199","article-title":"Learning to compare: relation network for few-shot learning","author":"Sung","year":"2018"},{"key":"10.1016\/j.neucom.2026.134090_bib0210","doi-asserted-by":"crossref","first-page":"4285","DOI":"10.1109\/TMM.2020.3039329","article-title":"Learning dual-pooling graph neural networks for few-shot video classification","volume":"23","author":"Hu","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134090_bib0215","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"6230","article-title":"Task-adaptive spatial-temporal video sampler for few-shot action recognition","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134090_bib0220","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8484","article-title":"Unsupervised few-shot action recognition via action-appearance aligned meta-adaptation","author":"Patravali","year":"2021"},{"key":"10.1016\/j.neucom.2026.134090_bib0225","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"7073","article-title":"Learning temporal action proposals with fewer labels","author":"Ji","year":"2019"},{"key":"10.1016\/j.neucom.2026.134090_bib0230","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10618","article-title":"Few-shot video classification via temporal alignment","author":"Cao","year":"2020"},{"key":"10.1016\/j.neucom.2026.134090_bib0235","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9151","article-title":"Motion-modulated temporal fragment alignment network for few-shot action recognition","author":"Wu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134090_bib0240","doi-asserted-by":"crossref","first-page":"5932","DOI":"10.1109\/TCSVT.2023.3262670","article-title":"Task-aware dual-representation network for few-shot action recognition","volume":"33","author":"Wang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134090_bib0245","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Kolesnikov","year":"2021"},{"key":"10.1016\/j.neucom.2026.134090_bib0250","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"815","article-title":"Facenet: a unified embedding for face recognition and clustering","author":"Schroff","year":"2015"},{"key":"10.1016\/j.neucom.2026.134090_bib0255","author":"Kay"},{"key":"10.1016\/j.neucom.2026.134090_bib0260","author":"Soomro"},{"key":"10.1016\/j.neucom.2026.134090_bib0265","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.2026.134090_bib0270","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.2026.134090_bib0275","series-title":"European Conference on Computer Vision","first-page":"20","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"Wang","year":"2016"},{"key":"10.1016\/j.neucom.2026.134090_bib0280","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134090_bib0285","series-title":"International Conference on Machine Learning","first-page":"5200","article-title":"SGD: general analysis and improved rates","author":"Gower","year":"2019"},{"key":"10.1016\/j.neucom.2026.134090_bib0290","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"2243","article-title":"On the importance of spatial relations for few-shot action recognition","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134090_bib0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103911","article-title":"Hierarchical compositional representations for few-shot action recognition","volume":"240","author":"Li","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.neucom.2026.134090_bib0300","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128044","article-title":"Task-specific alignment and multiple-level transformer for few-shot action recognition","volume":"598","author":"Guo","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134090_bib0305","series-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","article-title":"Dynamic temporal shift feature enhancement for few-shot action recognition","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.134090_bib0310","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129467","article-title":"Hierarchical task-aware temporal modeling and matching for few-shot action recognition","volume":"624","author":"Zhan","year":"2025","journal-title":"Neurocomputing"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014888?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014888?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:50:27Z","timestamp":1784202627000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226014888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":62,"alternative-id":["S0925231226014888"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134090","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":"Enhancing CrossTransformer with fine-grained spatio-temporal modeling for few-shot action recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134090","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":"134090"}}