{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:31:02Z","timestamp":1783823462130,"version":"3.55.0"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276186"],"award-info":[{"award-number":["62276186"]}],"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":["61925602"],"award-info":[{"award-number":["61925602"]}],"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":["61971086"],"award-info":[{"award-number":["61971086"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese Association for Artificial Intelligence (CAAI)-Huawei MindSpore Open Fund","award":["CAAIXSJLJJ-2022-010C"],"award-info":[{"award-number":["CAAIXSJLJJ-2022-010C"]}]},{"name":"Haihe Laboratory of Information Technology Application Innovation","award":["22HHX-CJC00002"],"award-info":[{"award-number":["22HHX-CJC00002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tnnls.2023.3321141","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T17:46:48Z","timestamp":1697132808000},"page":"18731-18745","source":"Crossref","is-referenced-by-count":14,"title":["AMS-Net: Modeling Adaptive Multi-Granularity Spatio-Temporal Cues for Video Action Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3765-9787","authenticated-orcid":false,"given":"Qilong","family":"Wang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyao","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7229-3867","authenticated-orcid":false,"given":"Peihua","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8095","authenticated-orcid":false,"given":"Qinghua","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3190367"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref4","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume-title":"Proc. NeurIPS","author":"Bulat"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2740318"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191461"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01182"},{"key":"ref10","volume-title":"OpenMMLab\u2019s Next Generation Video Understanding Toolbox and Benchmark","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref13","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref14","first-page":"2261","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","volume-title":"Proc. NeurIPS","author":"Fan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00470"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref17","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. NeurIPS","author":"Feichtenhofer"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041018"},{"key":"ref20","first-page":"13587","article-title":"Temporal-attentive covariance pooling networks for video recognition","volume-title":"Proc. NeurIPS","author":"Gao"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01243"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00302"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01212"},{"key":"ref33","first-page":"8046","article-title":"Relational self-attention: What\u2019s missing in attention for video understanding","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01282"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506157"},{"key":"ref37","first-page":"1","article-title":"Combined CNN transformer encoder for enhanced fine-grained human action recognition","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization (FGVC)","author":"Leong"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00609"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018618"},{"key":"ref40","article-title":"CT-Net: Channel tensorization network for video classification","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912001"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104244"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref46","first-page":"8674","article-title":"Temporal bilinear networks for video action recognition","volume-title":"Proc. AAAI","author":"Li"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref48","article-title":"Adaptive recursive circle framework for fine-grained action recognition","author":"Lin","year":"2021","journal-title":"arXiv:2107.11813"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105280"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_59"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01465"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3173473"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01122"},{"key":"ref62","first-page":"12496","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. NeurIPS","author":"Patrick"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3263288"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref67","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. NeurIPS","author":"Simonyan"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533515"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01661-1"},{"key":"ref72","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. NeurIPS","author":"Tong"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2917283"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"ref87","first-page":"6511","article-title":"Compact generalized non-local network","volume-title":"Proc. NeurIPS","author":"Yue"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_44"},{"key":"ref90","article-title":"V4D: 4D convolutional neural networks for video-level representation learning","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105184"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978613"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3126645"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.147"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00359"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_34"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10772360\/10283898.pdf?arnumber=10283898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T01:53:56Z","timestamp":1733882036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10283898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":99,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3321141","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}