{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T08:02:47Z","timestamp":1784707367311,"version":"3.55.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":84,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Open Innovation Fund of China National Engineering Research Center for Aluminum Metallurgy","award":["No. 202511SZS-WT-014"],"award-info":[{"award-number":["No. 202511SZS-WT-014"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s44443-026-00683-w","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T12:07:46Z","timestamp":1777464466000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-order evolution and adaptive geometric alignment via state spaces duality for few-shot action recognition"],"prefix":"10.1007","volume":"38","author":[{"given":"Shihang","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baowei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangman","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"683_CR1","doi-asserted-by":"crossref","unstructured":"Abdalla M, Javed S, Radi M, Ulhaq A, Werghi N (2024) Video anomaly detection in 10 years: A survey and outlook. arXiv:2405.19387","DOI":"10.1007\/s00521-025-11659-8"},{"key":"683_CR2","doi-asserted-by":"crossref","unstructured":"Cao K, Ji J, Cao Z, Chang C-Y, Niebles JC (2020) Few-shot video classification via temporal alignment. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10618\u201310627","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"683_CR3","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"683_CR4","unstructured":"Dao T, Gu A (2024) Transformers are ssms: Generalized models and efficient algorithms through structured state space duality. arXiv:2405.21060"},{"key":"683_CR5","unstructured":"Demrozi F, Turetta C, Machot FA, Pravadelli G, Kindt PH (2023) A comprehensive review of automated data annotation techniques in human activity recognition. arXiv:2307.05988"},{"key":"683_CR6","unstructured":"Dosovitskiy A (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929"},{"key":"683_CR7","doi-asserted-by":"crossref","unstructured":"Goyal R, Ebrahimi Kahou S, Michalski V, Materzynska J, Westphal S, Kim H, Haenel V, Fruend I, Yianilos P, Mueller-Freitag M et al (2017) The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: Proceedings of the IEEE international conference on computer vision, pp 5842\u20135850","DOI":"10.1109\/ICCV.2017.622"},{"key":"683_CR8","unstructured":"Gu A, Dao T (2024) Mamba: Linear-time sequence modeling with selective state spaces. In: First conference on language modeling"},{"key":"683_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128044","volume":"598","author":"F Guo","year":"2024","unstructured":"Guo F, Zhu L, Wang Y, Sun J (2024) Task-specific alignment and multiple-level transformer for few-shot action recognition. Neurocomputing 598:128044","journal-title":"Neurocomputing"},{"key":"683_CR10","doi-asserted-by":"crossref","unstructured":"Guo H, Yu W, Yan Y, Wang H (2024) Bi-directional motion attention with contrastive learning for few-shot action recognition. In: ICASSP 2024\u20132024 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 5490\u20135494","DOI":"10.1109\/ICASSP48485.2024.10447209"},{"key":"683_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128649","volume":"611","author":"F Guo","year":"2025","unstructured":"Guo F, Wang Y, Qi H, Zhu L, Sun J (2025) Consistency prototype module and motion compensation for few-shot action recognition (clip-cpm2c). Neurocomputing 611:128649","journal-title":"Neurocomputing"},{"key":"683_CR12","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Kautz J (2025) Mambavision: A hybrid mamba-transformer vision backbone. In: Proceedings of the computer vision and pattern recognition conference, pp 25261\u201325270","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"683_CR13","doi-asserted-by":"crossref","unstructured":"Huang Y, Yang L, Sato Y (2022) Compound prototype matching for few-shot action recognition. In: European conference on computer vision. Springer, pp 351\u2013368","DOI":"10.1007\/978-3-031-19772-7_21"},{"key":"683_CR14","doi-asserted-by":"crossref","unstructured":"Huang W, Zhang J, Li G, Zhang L, Wang S, Dong F, Jin J, Ogawa T, Haseyama M (2025) Manta: Enhancing mamba for few-shot action recognition of long sub-sequence. In: Proceedings of the AAAI conference on artificial intelligence, vol 39, pp 3751\u20133759","DOI":"10.1609\/aaai.v39i4.32391"},{"key":"683_CR15","unstructured":"Jaderberg M, Simonyan K, Zisserman A et al (2015) Spatial transformer networks. Adv Neural Inf Process Syst 28"},{"key":"683_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127819","volume":"598","author":"L Jiang","year":"2024","unstructured":"Jiang L, Zhan Y, Jiang Z, Tang N (2024) A dual-prototype network combining query-specific and class-specific attentive learning for few-shot action recognition. Neurocomputing 598:127819","journal-title":"Neurocomputing"},{"key":"683_CR17","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) Hmdb: a large video database for human motion recognition. In: 2011 International conference on computer vision. IEEE, pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"683_CR18","doi-asserted-by":"crossref","unstructured":"Kumar P, Padmanabhan N, Luo L, Rambhatla SS, Shrivastava A (2024) Trajectory-aligned space-time tokens for few-shot action recognition. In: European conference on computer vision. Springer, pp 474\u2013493","DOI":"10.1007\/978-3-031-72764-1_27"},{"key":"683_CR19","doi-asserted-by":"crossref","unstructured":"Li S, Liu H, Qian R, Li Y, See J, Fei M, Yu X, Lin W (2022) Ta2n: Two-stage action alignment network for few-shot action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 1404\u20131411","DOI":"10.1609\/aaai.v36i2.20029"},{"key":"683_CR20","unstructured":"Lieber O, Lenz B, Bata H, Cohen G, Osin J, Dalmedigos I, Safahi E, Meirom S, Belinkov Y, Shalev-Shwartz S et al (2024) Jamba: A hybrid transformer-mamba language model. arXiv:2403.19887"},{"key":"683_CR21","doi-asserted-by":"crossref","unstructured":"Liu J, Song L, Qin Y (2020) Prototype rectification for few-shot learning. In: European conference on computer vision. Springer, pp 741\u2013756","DOI":"10.1007\/978-3-030-58452-8_43"},{"key":"683_CR22","doi-asserted-by":"crossref","unstructured":"Liu X, Zhang H, Pirsiavash H (2023) Mastaf: a model-agnostic spatio-temporal attention fusion network for few-shot video classification. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 2508\u20132517","DOI":"10.1109\/WACV56688.2023.00254"},{"key":"683_CR23","doi-asserted-by":"publisher","first-page":"103031","DOI":"10.52202\/079017-3273","volume":"37","author":"Y Liu","year":"2024","unstructured":"Liu Y, Tian Y, Zhao Y, Yu H, Xie L, Wang Y, Ye Q, Jiao J, Liu Y (2024) Vmamba: Visual state space model. Adv Neural Inf Process Syst 37:103031\u2013103063","journal-title":"Adv Neural Inf Process Syst"},{"key":"683_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen KD, Tran Q-H, Nguyen K, Hua B-S, Nguyen R (2022) Inductive and transductive few-shot video classification via appearance and temporal alignments. In: European conference on computer vision. Springer, pp 471\u2013487","DOI":"10.1007\/978-3-031-20044-1_27"},{"key":"683_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112375","volume":"167","author":"JJL Olmo","year":"2024","unstructured":"Olmo JJL, G\u00f3mez \u00c1LP, Lopez-de-Teruel PE, Ruiz A (2024) A few-shot learning methodology for improving safety in industrial scenarios through universal self-supervised visual features and dense optical flow. Appl Soft Comput 167:112375","journal-title":"Appl Soft Comput"},{"key":"683_CR26","unstructured":"Oreshkin B, Rodr\u00edguez L\u00f3pez P, Lacoste A (2018) Tadam: Task dependent adaptive metric for improved few-shot learning. Adv Neural Inf Process Syst 31"},{"key":"683_CR27","doi-asserted-by":"crossref","unstructured":"Perrett T, Masullo A, Burghardt T, Mirmehdi M, Damen D (2021) Temporal-relational crosstransformers for few-shot action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 475\u2013484","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"683_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106326","volume":"176","author":"Y Qin","year":"2024","unstructured":"Qin Y, Liu B (2024) Tfrs: A task-level feature rectification and separation method for few-shot video action recognition. Neural Netw 176:106326","journal-title":"Neural Netw"},{"issue":"13s","key":"683_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3577925","volume":"55","author":"MC Schiappa","year":"2023","unstructured":"Schiappa MC, Rawat YS, Shah M (2023) Self-supervised learning for videos: A survey. ACM Comput Surv 55(13s):1\u201337. https:\/\/doi.org\/10.1145\/3577925","journal-title":"ACM Comput Surv"},{"key":"683_CR30","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30"},{"key":"683_CR31","unstructured":"Soomro K, Zamir AR, Shah M (2012) Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402"},{"key":"683_CR32","doi-asserted-by":"crossref","unstructured":"Thatipelli A, Narayan S, Khan S, Anwer RM, Khan FS, Ghanem B (2022) Spatio-temporal relation modeling for few-shot action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19958\u201319967","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"683_CR33","unstructured":"Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. Adv Neural Inf Process Syst 29"},{"key":"683_CR34","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2016) Temporal segment networks: Towards good practices for deep action recognition. In: European conference on computer vision. Springer, pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"683_CR35","doi-asserted-by":"crossref","unstructured":"Wang X, Zhang S, Qing Z, Tang M, Zuo Z, Gao C, Jin R, Sang N (2022) Hybrid relation guided set matching for few-shot action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19948\u201319957","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"683_CR36","doi-asserted-by":"crossref","unstructured":"Wang X, Zhang S, Qing Z, Gao C, Zhang Y, Zhao D, Sang N (2023) Molo: Motion-augmented long-short contrastive learning for few-shot action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18011\u201318021","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"683_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110110","volume":"147","author":"X Wang","year":"2024","unstructured":"Wang X, Zhang S, Qing Z, Zuo Z, Gao C, Jin R, Sang N (2024) Hyrsm++: Hybrid relation guided temporal set matching for few-shot action recognition. Pattern Recogn 147:110110","journal-title":"Pattern Recogn"},{"key":"683_CR38","unstructured":"Wang J, Gangavarapu T, Yan JN, Rush AM (2024) Mambabyte: Token-free selective state space model. arXiv:2401.13660"},{"issue":"1","key":"683_CR39","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1080\/24699322.2021.1937320","volume":"26","author":"TM Ward","year":"2021","unstructured":"Ward TM, Fer DM, Ban Y, Rosman G, Meireles OR, Hashimoto DA (2021) Challenges in surgical video annotation. Comput Assist Surgery 26(1):58\u201368","journal-title":"Comput Assist Surgery"},{"key":"683_CR40","doi-asserted-by":"crossref","unstructured":"Xia H, Li K, Min MR, Ding Z (2023) Few-shot video classification via representation fusion and promotion learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 19311\u201319320","DOI":"10.1109\/ICCV51070.2023.01769"},{"key":"683_CR41","doi-asserted-by":"crossref","unstructured":"Xing J, Wang M, Liu Y, Mu B (2023) Revisiting the spatial and temporal modeling for few-shot action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 37, pp 3001\u20133009","DOI":"10.1609\/aaai.v37i3.25403"},{"key":"683_CR42","doi-asserted-by":"crossref","unstructured":"Yu W, Wang X (2025) Mambaout: Do we really need mamba for vision? In: Proceedings of the computer vision and pattern recognition conference, pp 4484\u20134496","DOI":"10.1109\/CVPR52734.2025.00423"},{"key":"683_CR43","doi-asserted-by":"crossref","unstructured":"Yuan D, Liu J, Li B, Zhang H, Wang J, Cai X, Zhao D (2024) Remamba: Equip mamba with effective long-sequence modeling. arXiv:2408.15496","DOI":"10.18653\/v1\/2025.findings-emnlp.361"},{"key":"683_CR44","doi-asserted-by":"crossref","unstructured":"Zhang H, Zhang L, Qi X, Li H, Torr PH, Koniusz P (2020) Few-shot action recognition with permutation-invariant attention. In: European conference on computer vision. Springer, pp 525\u2013542","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"683_CR45","doi-asserted-by":"crossref","unstructured":"Zhu L, Yang Y (2018) Compound memory networks for few-shot video classification. In: Proceedings of the European conference on computer vision (ECCV), pp 751\u2013766","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"683_CR46","unstructured":"Zhu L, Liao B, Zhang Q, Wang X, Liu W, Wang X (2024) Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv:2401.09417"},{"key":"683_CR47","doi-asserted-by":"crossref","unstructured":"Zou Y, Zhang S, Chen G, Tian Y, Keutzer K, Moura JM (2021) Annotation-efficient untrimmed video action recognition. In: Proceedings of the 29th ACM international conference on multimedia, pp 487\u2013495","DOI":"10.1145\/3474085.3475197"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00683-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00683-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00683-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T07:31:56Z","timestamp":1784705516000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00683-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":47,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["683"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00683-w","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"assertion":[{"value":"21 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing Interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable (as this study uses publicly available datasets).","order":2,"name":"Ethics","label":"Ethical Approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"369"}}