{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T15:47:47Z","timestamp":1782229667037,"version":"3.54.5"},"reference-count":54,"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.2026.134287","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:29:37Z","timestamp":1781713777000},"page":"134287","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-level matcher based on multi-modal for few-shot action recognition"],"prefix":"10.1016","volume":"698","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0960-4024","authenticated-orcid":false,"given":"Nan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Qi","sequence":"additional","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.neucom.2026.134287_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"2786","article-title":"Temporal aware embedding network for few-shot action recognition","author":"Ben-Ari","year":"2021"},{"key":"10.1016\/j.neucom.2026.134287_bib0010","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.2026.134287_bib0015","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6299","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.neucom.2026.134287_bib0020","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134287_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113965","article-title":"CLIP-MEI: exploit more effective information for few-shot action recognition","volume":"326","author":"Deng","year":"2025","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.134287_bib0030","doi-asserted-by":"crossref","first-page":"3513","DOI":"10.1109\/TCSVT.2025.3621451","article-title":"Temporal consistency and variation-guided spatio-temporal aggregation for few-shot action recognition","volume":"36","author":"Dong","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134287_bib0035","series-title":"International Conference on Machine Learning","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"10.1016\/j.neucom.2026.134287_bib0040","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"1142","article-title":"Depth guided adaptive meta-fusion network for few-shot video recognition","author":"Fu","year":"2020"},{"key":"10.1016\/j.neucom.2026.134287_bib0045","doi-asserted-by":"crossref","first-page":"2450","DOI":"10.1109\/TMM.2024.3521712","article-title":"Hierarchical motion-enhanced matching framework for few-shot action recognition","volume":"27","author":"Gao","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134287_bib0050","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"5842","article-title":"The something something video database for learning and evaluating visual common sense","author":"Goyal","year":"2017"},{"key":"10.1016\/j.neucom.2026.134287_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112539","article-title":"Multi-view distillation based on multi-modal fusion for few-shot action recognition (CLIP-MDMF)","author":"Guo","year":"2024","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.134287_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110780","article-title":"Boosting meta-training with base class information for robust few-shot learning","volume":"152","author":"Jiang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134287_bib0065","series-title":"3rd International Conference on Learning Representations (ICLR)","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.neucom.2026.134287_bib0070","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.2026.134287_bib0075","first-page":"887","article-title":"Hierarchical compositional representations for few-shot action recognition","volume":"31","author":"Li","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.134287_bib0080","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","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.2026.134287_bib0085","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1016\/j.neucom.2022.11.082","article-title":"ReNAP: relation network with adaptiveprototypical learning for few-shot classification","volume":"520","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134287_bib0090","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"513","article-title":"Resound: towards action recognition without representation bias","author":"Li","year":"2018"},{"key":"10.1016\/j.neucom.2026.134287_bib0095","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"7283","article-title":"Lite-MKD: a multi-modal knowledge distillation framework for lightweight few-shot action recognition","author":"Liu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134287_bib0100","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/978-3-540-74048-3_4","article-title":"Dynamic time warping","author":"M\u00fcller","year":"2007","journal-title":"Inf. Retr. Music Motion"},{"key":"10.1016\/j.neucom.2026.134287_bib0105","author":"Ni"},{"key":"10.1016\/j.neucom.2026.134287_bib0110","author":"Perez"},{"key":"10.1016\/j.neucom.2026.134287_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"},{"key":"10.1016\/j.neucom.2026.134287_bib0120","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.neucom.2022.09.011","article-title":"KDM: a knowledge-guided and data-driven method for few-shot video action recognition","volume":"510","author":"Qin","year":"2022","journal-title":"Neurocomputing"},{"issue":"7","key":"10.1016\/j.neucom.2026.134287_bib0125","doi-asserted-by":"crossref","first-page":"7954","DOI":"10.1109\/TPAMI.2026.3669254","article-title":"Spatio-temporal decoupled knowledge compensator for few-shot action recognition","volume":"48","author":"Qu","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134287_bib0130","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.2026.134287_bib0135","series-title":"International Conference on Learning Representations","article-title":"Optimization as a model for few-shot learning","author":"Ravi","year":"2017"},{"key":"10.1016\/j.neucom.2026.134287_bib0140","first-page":"1","article-title":"Improving the generalization of MAML in few-shot classification via bi-level constraint","author":"Shao","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134287_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4136","article-title":"Adaptive subspaces for few-shot learning","author":"Simon","year":"2020"},{"key":"10.1016\/j.neucom.2026.134287_bib0150","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134287_bib0155","author":"Soomro"},{"key":"10.1016\/j.neucom.2026.134287_bib0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2020.102380","article-title":"Vdarn: video disentangling attentive relation network for few-shot and zero-shot action recognition","volume":"113","author":"Su","year":"2021","journal-title":"Ad Hoc Netw."},{"key":"10.1016\/j.neucom.2026.134287_bib0165","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.2026.134287_bib0170","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","article-title":"M3Net: multi-view encoding, matching, and fusion for few-shot fine-grained action recognition","author":"Tang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134287_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19958","article-title":"Spatio-temporal relation modeling for few-shot action recognition","author":"Thatipelli","year":"2022"},{"key":"10.1016\/j.neucom.2026.134287_bib0180","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.2026.134287_bib0185","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"2879","article-title":"Few-shot fine-grained action recognition via bidirectional attention and contrastive meta-learning","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134287_bib0190","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.2026.134287_bib0195","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1109\/TIP.2024.3354104","article-title":"Cross-modal contrastive learning network for few-shot action recognition","volume":"33","author":"Wang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.134287_bib0200","first-page":"1","article-title":"Task-aware dual-representation network for few-shot action recognition","author":"Wang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134287_bib0205","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"816","article-title":"Semantic-guided relation propagation network for few-shot action recognition","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134287_bib0210","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134287_bib0215","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134287_bib0220","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19948","article-title":"Hybrid relation guided set matching for few-shot action recognition","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134287_bib0225","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6492","article-title":"Active exploration of multimodal complementarity for few-shot action recognition","author":"Wanyan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134287_bib0230","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1109\/TCSVT.2021.3077512","article-title":"Spatiotemporal multimodal learning with 3D CNNs for video action recognition","volume":"32","author":"Wu","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134287_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.2026.134287_bib0240","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127582","article-title":"Mask guided two-stream network for end-to-end few-shot action recognition","volume":"583","author":"Xie","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134287_bib0245","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.2026.134287_bib0250","first-page":"1","article-title":"DPCA-net: dual-prototype consistency alignment network for robust multimodal few-shot action recognition","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134287_bib0255","series-title":"Computer Vision\u2013ECCV 2022: 17th European Conference","first-page":"297","article-title":"Few-shot action recognition with hierarchical matching and contrastive learning","author":"Zheng","year":"2022"},{"key":"10.1016\/j.neucom.2026.134287_bib0260","series-title":"European Conference on Computer Vision","first-page":"297","article-title":"Few-shot action recognition with hierarchical matching and contrastive learning","author":"Zheng","year":"2022"},{"key":"10.1016\/j.neucom.2026.134287_bib0265","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.2026.134287_bib0270","first-page":"273","article-title":"Label independent memory for semi-supervised few-shot video classification","volume":"44","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016851?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016851?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T15:20:18Z","timestamp":1782228018000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226016851"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":54,"alternative-id":["S0925231226016851"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134287","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":"Multi-level matcher based on multi-modal 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.2026.134287","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134287"}}