{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T17:06:40Z","timestamp":1774976800499,"version":"3.50.1"},"reference-count":71,"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":["61991411"],"award-info":[{"award-number":["61991411"]}],"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":["62076148"],"award-info":[{"award-number":["62076148"]}],"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":["U22A2057"],"award-info":[{"award-number":["U22A2057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Plan of China","award":["2021ZD0112002"],"award-info":[{"award-number":["2021ZD0112002"]}]},{"name":"Shandong Excellent Young Scientists Fund Program","award":["2022HWYQ-042"],"award-info":[{"award-number":["2022HWYQ-042"]}]},{"name":"Self-Developed Innovation Team of Jinan City","award":["2021GXRC038"],"award-info":[{"award-number":["2021GXRC038"]}]},{"name":"Young Taishan Scholars Program of Shandong Province","award":["tsqn201909029"],"award-info":[{"award-number":["tsqn201909029"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3395778","type":"journal-article","created":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T13:22:57Z","timestamp":1714656177000},"page":"7728-7741","source":"Crossref","is-referenced-by-count":16,"title":["DeTAL: Open-Vocabulary Temporal Action Localization With Decoupled Networks"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5288-4325","authenticated-orcid":false,"given":"Zhiheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9127-3387","authenticated-orcid":false,"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1344-4415","authenticated-orcid":false,"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7912-5281","authenticated-orcid":false,"given":"Tianjiao","family":"Li","sequence":"additional","affiliation":[{"name":"Information Systems Technology and Design, Singapore University of Technology and Design, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-6132","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193611"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.52"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref8","article-title":"Low-fidelity end-to-end video encoder pre-training for temporal action localization","author":"Xu","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00096"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00125"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00394"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183586"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref16","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref17","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_20"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093612"},{"key":"ref22","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2582379"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref30","article-title":"FitCLIP: Refining large-scale pretrained image-text models for zero-shot video understanding tasks","author":"Castro","year":"2022"},{"key":"ref31","first-page":"21455","article-title":"Quality not quantity: On the interaction between dataset design and robustness of clip","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref34","article-title":"Activity graph transformer for temporal action localization","author":"Nawhal","year":"2021"},{"key":"ref35","article-title":"Adaptive perception transformer for temporal action localization","author":"Ouyang","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6829"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01326"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref47","article-title":"Temporal action proposal generation with transformers","author":"Wang","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref49","article-title":"Augmented transformer with adaptive graph for temporal action proposal generation","author":"Chang","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350760"},{"key":"ref52","article-title":"word2vec explained: Deriving Mikolov et al.\u2019s negative-sampling word-embedding method","author":"Goldberg","year":"2014"},{"key":"ref53","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/980451.980860"},{"key":"ref56","article-title":"Frame semantics for text understanding","volume-title":"Proc. WordNet Lexical Resour. Workshop","author":"Fillmore"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref62","article-title":"TemporalMaxer: Maximize temporal context with only max pooling for temporal action localization","author":"Tang","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"ref70","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10746266\/10517407.pdf?arnumber=10517407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:43:34Z","timestamp":1755546214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10517407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":71,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3395778","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":[[2024,12]]}}}