{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:29:38Z","timestamp":1776889778121,"version":"3.51.2"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004377","name":"The Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["R-ZDF9"],"award-info":[{"award-number":["R-ZDF9"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003803","name":"RGC of Hong Kong","doi-asserted-by":"publisher","award":["15228223"],"award-info":[{"award-number":["15228223"]}],"id":[{"id":"10.13039\/501100003803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3451503","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T17:57:26Z","timestamp":1724954246000},"page":"126829-126844","source":"Crossref","is-referenced-by-count":4,"title":["Action Progression Networks for Temporal Action Detection in Videos"],"prefix":"10.1109","volume":"12","author":[{"given":"Chong-Kai","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronical Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man-Wai","family":"Mak","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronical Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2393-2225","authenticated-orcid":false,"given":"Ruimin","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0714-8713","authenticated-orcid":false,"given":"Zheru","family":"Chi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronical Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2246-7552","authenticated-orcid":false,"given":"Hong","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"CISCO visual networking index (VNI) complete forecast update","author":"Barnett","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3247820"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-023-01179-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111852"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"arXiv:1409.1556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref11","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"He"},{"key":"ref12","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref13","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref16","first-page":"1817","article-title":"Action and event recognition with Fisher vectors on a compact feature set","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Oneata"},{"key":"ref17","article-title":"The LEAR submission at Thumos 2014","author":"Oneata","year":"2014"},{"issue":"2","key":"ref18","first-page":"2","article-title":"Action recognition and detection by combining motion and appearance features","volume":"1","author":"Wang","year":"2014","journal-title":"THUMOS14 Action Recognit. Challenge"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465908"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref23","article-title":"Untrimmed video classification for activity detection: Submission to ActivityNet challenge","author":"Singh","year":"2016","journal-title":"arXiv:1607.01979"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.5244\/C.31.93","article-title":"End-to-end, single-stream temporal action detection in untrimmed videos","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Buch"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"issue":"7","key":"ref30","first-page":"11499","article-title":"Fast learning of temporal action proposal via dense boundary generator","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Lin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60639-8_4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330794"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206029"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref40","article-title":"Progress regression RNN for online spatial\u2013temporal action localization in unconstrained videos","author":"Hu","year":"2019","journal-title":"arXiv:1903.00304"},{"key":"ref41","article-title":"LAP-Net: Adaptive features sampling via learning action progression for online action detection","author":"Qu","year":"2020","journal-title":"arXiv:2011.07915"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2457911"},{"key":"ref43","article-title":"Rank-consistent ordinal regression for neural networks","author":"Cao","year":"2019","journal-title":"arXiv:1901.07884"},{"key":"ref44","volume-title":"THUMOS Challenge: Action Recognition With a Large Number of Classes","author":"Jiang","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103692"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00125"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806226"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00400"},{"key":"ref54","first-page":"8678","article-title":"3C-net: Category count and center loss for weakly-supervised action localization","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Narayan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_17"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_43"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_3"},{"key":"ref59","article-title":"ACM-Net: Action context modeling network for weakly-supervised temporal action localization","author":"Qu","year":"2021","journal-title":"arXiv:2104.02967"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16280"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00595"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109135"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611872"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12234"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01938"},{"key":"ref68","first-page":"3648","article-title":"TURN TAP: Temporal unit regression network for temporal action proposals","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Gao"},{"key":"ref69","article-title":"S3D: Single shot multi-span detector via fully 3D convolutional networks","author":"Zhang","year":"2018","journal-title":"arXiv:1807.08069"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5893"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6829"},{"key":"ref72","article-title":"RGB stream is enough for temporal action detection","author":"Wang","year":"2021","journal-title":"arXiv:2107.04362"},{"key":"ref73","article-title":"Towards high-quality temporal action detection with sparse proposals","author":"Wu","year":"2021","journal-title":"arXiv:2109.08847"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3195321"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00944"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00951"},{"key":"ref79","article-title":"AFO-TAD: Anchor-free one-stage detector for temporal action detection","author":"Tang","year":"2019","journal-title":"arXiv:1910.08250"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"ref81","article-title":"Human action forecasting by learning task grammars","author":"Han","year":"2017","journal-title":"arXiv:1709.06391"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3130936"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01234"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3402447"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00128"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3390\/s23010520"},{"key":"ref87","first-page":"2958","article-title":"Is there progress in activity progress prediction?","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV) Workshops","author":"Dijkstra"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.532"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412081"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref93","first-page":"250","article-title":"Online ranking\/collaborative filtering using the perceptron algorithm","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Harrington"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1971.223290"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2019.2911303"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref97","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref98","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref99","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019","journal-title":"arXiv:1907.06987"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"ref105","volume-title":"A Recipe for Training Neural Networks","author":"Karpathy","year":"2019"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10658640.pdf?arnumber=10658640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T06:29:32Z","timestamp":1726640972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10658640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3451503","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}