{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T03:57:46Z","timestamp":1783483066165,"version":"3.55.0"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0160900"],"award-info":[{"award-number":["2022ZD0160900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076119"],"award-info":[{"award-number":["62076119"]}],"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":["61921006"],"award-info":[{"award-number":["61921006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214380099"],"award-info":[{"award-number":["020214380099"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tpami.2024.3387127","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T18:14:27Z","timestamp":1712772867000},"page":"6842-6857","source":"Crossref","is-referenced-by-count":5,"title":["STMixer: A One-Stage Sparse Action Detector"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1028-6919","authenticated-orcid":false,"given":"Tao","family":"Wu","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8108-0664","authenticated-orcid":false,"given":"Mengqi","family":"Cao","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6815-6209","authenticated-orcid":false,"given":"Ziteng","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1391-1762","authenticated-orcid":false,"given":"Gangshan","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref2","article-title":"Human centric spatio-temporal action localization","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Jiang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.296"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00288"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref8","article-title":"The AVA-kinetics localized human actions video dataset","author":"Li","year":"2020"},{"key":"ref9","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01328"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref19","article-title":"V4D: 4D convolutional neural networks for video-level representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref27","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tong"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"ref33","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00529"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01414"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00334"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_27"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref46","article-title":"You only watch once: A unified CNN architecture for real-time spatiotemporal action localization","author":"K\u00f6p\u00fckl\u00fc","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00035"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"ref60","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref61","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref64","article-title":"Efficient DETR: Improving end-to-end object detector with dense prior","author":"Yao","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref66","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01896"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00109"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01893"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref78","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_21"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref83","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref85","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref86","first-page":"24 261","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref87","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref89","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref90","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref91","article-title":"Pyslowfast","author":"Fan","year":"2020"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref93","article-title":"Beyond transfer learning: Co-finetuning for action localisation","author":"Arnab","year":"2022"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.58"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_30"},{"key":"ref97","article-title":"Person-context cross attention for spatio-temporal action detection","author":"Ning","year":"2021"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00595"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10666888\/10496238.pdf?arnumber=10496238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:46:14Z","timestamp":1725684374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":98,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3387127","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}