{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:58:16Z","timestamp":1780934296134,"version":"3.54.1"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008990","name":"Science and Technology Department of Zhejiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008990","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.113940","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T06:46:40Z","timestamp":1779173200000},"page":"113940","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Frequency-adaptive experts with deep-to-shallow guidance for temporal action detection"],"prefix":"10.1016","volume":"180","author":[{"given":"Lizao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-4437","authenticated-orcid":false,"given":"Qiuhong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengzheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113940_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109453","article-title":"A survey of human\u2013computer interaction (hci) & natural habits-based behavioural biometric modalities for user recognition schemes","volume":"139","author":"Gupta","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113940_b2","series-title":"European Conference on Computer Vision","first-page":"492","article-title":"Actionformer: Localizing moments of actions with transformers","author":"Zhang","year":"2022"},{"issue":"3","key":"10.1016\/j.patcog.2026.113940_b3","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1109\/TIT.1960.1057571","article-title":"An introduction to matched filters","volume":"6","author":"Turin","year":"2003","journal-title":"IRE Trans. Inf. Theory"},{"key":"10.1016\/j.patcog.2026.113940_b4","doi-asserted-by":"crossref","unstructured":"D. Shi, Y. Zhong, Q. Cao, L. Ma, J. Li, D. Tao, Tridet: Temporal action detection with relative boundary modeling, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18857\u201318866.","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"10.1016\/j.patcog.2026.113940_b5","series-title":"European Conference on Computer Vision","first-page":"305","article-title":"Dyfadet: Dynamic feature aggregation for temporal action detection","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113940_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109684","article-title":"Truncated attention-aware proposal networks with multi-scale dilation for temporal action detection","volume":"142","author":"Li","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113940_b7","doi-asserted-by":"crossref","unstructured":"T. Lin, X. Liu, X. Li, E. Ding, S. Wen, Bmn: Boundary-matching network for temporal action proposal generation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 3889\u20133898.","DOI":"10.1109\/ICCV.2019.00399"},{"key":"10.1016\/j.patcog.2026.113940_b8","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"issue":"4","key":"10.1016\/j.patcog.2026.113940_b9","doi-asserted-by":"crossref","first-page":"2171","DOI":"10.1109\/TPAMI.2023.3330794","article-title":"Temporal action localization in the deep learning era: A survey","volume":"46","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113940_b10","doi-asserted-by":"crossref","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","article-title":"End-to-end temporal action detection with transformer","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113940_b11","doi-asserted-by":"crossref","unstructured":"H.-J. Kim, J.-H. Hong, H. Kong, S.-W. Lee, Te-tad: Towards full end-to-end temporal action detection via time-aligned coordinate expression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18837\u201318846.","DOI":"10.1109\/CVPR52733.2024.01782"},{"issue":"10","key":"10.1016\/j.patcog.2026.113940_b12","doi-asserted-by":"crossref","first-page":"6209","DOI":"10.1109\/TPAMI.2021.3090167","article-title":"Graph convolutional module for temporal action localization in videos","volume":"44","author":"Zeng","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113940_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109135","article-title":"Video representation learning for temporal action detection using global-local attention","volume":"134","author":"Tang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113940_b14","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.113940_b15","series-title":"2018 24th International Conference on Pattern Recognition (Icpr)","first-page":"373","article-title":"Ld-cnn: A lightweight dilated convolutional neural network for environmental sound classification","author":"Zhang","year":"2018"},{"issue":"10","key":"10.1016\/j.patcog.2026.113940_b16","doi-asserted-by":"crossref","first-page":"2495","DOI":"10.1109\/TPAMI.2018.2857824","article-title":"Packing convolutional neural networks in the frequency domain","volume":"41","author":"Wang","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113940_b17","article-title":"Dilatedtad: Enhancing adaptability to actions of varying durations for temporal action detection","author":"Tang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113940_b18","unstructured":"A. Gu, T. Dao, Mamba: Linear-time sequence modeling with selective state spaces, in: First Conference on Language Modeling, 2024."},{"key":"10.1016\/j.patcog.2026.113940_b19","series-title":"Video mamba suite: State space model as a versatile alternative for video understanding","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.113940_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111846","article-title":"Feature matters: Revisiting channel attention for temporal action detection","volume":"169","author":"Chen","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113940_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111644","article-title":"A dynamic predictive transformer with temporal relevance regression for action detection","volume":"166","author":"Korban","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113940_b22","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.patrec.2023.06.013","article-title":"A handwritten ancient text detector based on improved feature pyramid network","volume":"172","author":"Feng","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.113940_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111209","article-title":"Bifpn-yolo: One-stage object detection integrating bi-directional feature pyramid networks","volume":"160","author":"Doherty","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113940_b24","article-title":"Uni-moe: Scaling unified multimodal llms with mixture of experts","author":"Li","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113940_b25","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.patcog.2018.07.020","article-title":"Moe-spnet: A mixture-of-experts scene parsing network","volume":"84","author":"Fu","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113940_b26","first-page":"58480","article-title":"Mixture of nested experts: Adaptive processing of visual tokens","volume":"37","author":"Jain","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113940_b27","series-title":"European Conference on Computer Vision","first-page":"380","article-title":"Occluded gait recognition with mixture of experts: an action detection perspective","author":"Huang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113940_b28","doi-asserted-by":"crossref","unstructured":"N. Bodla, B. Singh, R. Chellappa, L.S. Davis, Soft-nms\u2013improving object detection with one line of code, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5561\u20135569.","DOI":"10.1109\/ICCV.2017.593"},{"key":"10.1016\/j.patcog.2026.113940_b29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","article-title":"The thumos challenge on action recognition for videos \u201cin the wild\u201d","volume":"155","author":"Idrees","year":"2017","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.113940_b30","doi-asserted-by":"crossref","unstructured":"F. Caba Heilbron, V. Escorcia, B. Ghanem, J. Carlos Niebles, Activitynet: A large-scale video benchmark for human activity understanding, in: Proceedings of the Ieee Conference on Computer Vision and Pattern Recognition, 2015, pp. 961\u2013970.","DOI":"10.1109\/CVPR.2015.7298698"},{"issue":"2","key":"10.1016\/j.patcog.2026.113940_b31","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/s11263-017-1013-y","article-title":"Every moment counts: Dense detailed labeling of actions in complex videos","volume":"126","author":"Yeung","year":"2018","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113940_b32","doi-asserted-by":"crossref","unstructured":"D. Damen, H. Doughty, G.M. Farinella, S. Fidler, A. Furnari, E. Kazakos, D. Moltisanti, J. Munro, T. Perrett, W. Price, et al., Scaling egocentric vision: The epic-kitchens dataset, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 720\u2013736.","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"10.1016\/j.patcog.2026.113940_b33","doi-asserted-by":"crossref","unstructured":"M. Xu, C. Zhao, D.S. Rojas, A. Thabet, B. Ghanem, G-tad: Sub-graph localization for temporal action detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10156\u201310165.","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"10.1016\/j.patcog.2026.113940_b34","doi-asserted-by":"crossref","unstructured":"C. Zhao, A.K. Thabet, B. Ghanem, Video self-stitching graph network for temporal action localization, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13658\u201313667.","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"10.1016\/j.patcog.2026.113940_b35","unstructured":"T.N. Tang, K. Kim, K. Sohn, Temporalmaxer: Maximize temporal context with only max pooling for temporal action localization, in: Proceedings of the British Machine Vision Conference, BMVC, 2023."},{"key":"10.1016\/j.patcog.2026.113940_b36","doi-asserted-by":"crossref","unstructured":"J. Shao, X. Wang, R. Quan, J. Zheng, J. Yang, Y. Yang, Action sensitivity learning for temporal action localization, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 13457\u201313469.","DOI":"10.1109\/ICCV51070.2023.01238"},{"issue":"6","key":"10.1016\/j.patcog.2026.113940_b37","doi-asserted-by":"crossref","first-page":"4625","DOI":"10.1109\/TCSVT.2023.3326692","article-title":"Cross time-frequency transformer for temporal action localization","volume":"34","author":"Yang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113940_b38","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2025.3543108","article-title":"Boundary discretization and reliable classification network for temporal action detection","author":"Fang","year":"2025","journal-title":"IEEE Trans. Multimed."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009052?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009052?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:04:37Z","timestamp":1780931077000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":38,"alternative-id":["S0031320326009052"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113940","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Frequency-adaptive experts with deep-to-shallow guidance for temporal action detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113940","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113940"}}