{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:07:40Z","timestamp":1775326060333,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&amp;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":["020214380091"],"award-info":[{"award-number":["020214380091"]}],"id":[{"id":"10.13039\/501100012226","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":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3283067","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T02:44:53Z","timestamp":1686105893000},"page":"12506-12520","source":"Crossref","is-referenced-by-count":15,"title":["Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8016-915X","authenticated-orcid":false,"given":"Jing","family":"Tan","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2510-7940","authenticated-orcid":false,"given":"Yuhong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]},{"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, Jiangsu, China"}]},{"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, Jiangsu, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.111"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref56","first-page":"1","article-title":"Video scene segmentation using a novel boundary evaluation criterion and dynamic programming","author":"han","year":"2011","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref59","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics - Hum Lang Technol"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref58","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref53","first-page":"237","article-title":"Exploring video structure beyond the shots","author":"rui","year":"1998","journal-title":"Proc IEEE Int Conf Multimedia Comput Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3042476"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2008924"},{"key":"ref10","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2016.0061"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"ref45","article-title":"Pyscenedetect: Video scene cut detection and analysis tool","author":"castellano","year":"2014"},{"key":"ref48","first-page":"6508","article-title":"Weakly-supervised action segmentation with iterative soft boundary assignment","author":"ding","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01103"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00800"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref4","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"tong","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"ref5","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00967"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref74","article-title":"SC-Transformer++: Structured context transformer for generic event boundary detection","author":"hong","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6711"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"ref38","article-title":"Scikit-video: Video processing in python","author":"developers","year":"2015"},{"key":"ref71","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","article-title":"TransNet V2: An effective deep network architecture for fast shot transition detection","author":"sou?ek","year":"2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01314"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref68","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","author":"jaegle","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref69","article-title":"Perceiver IO: A general architecture for structured inputs & outputs","author":"jaegle","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref64","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","article-title":"Video swin transformer","author":"liu","year":"2021"},{"key":"ref22","first-page":"214","article-title":"Multi-modal transformer for video retrieval","author":"gabeur","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref66","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.327"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref60","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref61","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10144649.pdf?arnumber=10144649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:09:02Z","timestamp":1717693742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10144649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":75,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3283067","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":[[2023,10]]}}}