{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:52:30Z","timestamp":1775508750887,"version":"3.50.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62532003"],"award-info":[{"award-number":["62532003"]}],"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":["62325206"],"award-info":[{"award-number":["62325206"]}],"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":["62402243"],"award-info":[{"award-number":["62402243"]}],"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":["U23A20387"],"award-info":[{"award-number":["U23A20387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2023016-4"],"award-info":[{"award-number":["BE2023016-4"]}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20240646"],"award-info":[{"award-number":["BK20240646"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications","award":["NY223129"],"award-info":[{"award-number":["NY223129"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3653482","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:58:38Z","timestamp":1768337918000},"page":"5945-5962","source":"Crossref","is-referenced-by-count":0,"title":["Goal-Guided Prompting With Adaptive Modality Selection for Efficient Assembly Activity Anticipation in Egocentric Videos"],"prefix":"10.1109","volume":"48","author":[{"given":"Tianshan","family":"Liu","sequence":"first","affiliation":[{"name":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3368148"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3384657.3384799"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3675094.3678989"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101887"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3749513"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00161"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00206"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"ref13","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103764"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992889"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055233"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01353"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393730"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01302"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040521"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00254"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00601"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. on Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref29","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.132"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.616"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref36","article-title":"Diffant: Diffusion models for action anticipation","author":"Zhong","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_26"},{"key":"ref39","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref40","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref41","first-page":"1","article-title":"AntGPT: Can large language models help long-term action anticipation from videos?","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhao","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78354-8_11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222914"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00088"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2017.8227441"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01248"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01734"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01744"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3514654"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/98"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref68","first-page":"1","article-title":"Liteeval: A coarse-to-fine framework for resource efficient video recognition","volume":"32","author":"Wu","year":"2019","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_14"},{"key":"ref74","first-page":"28618","article-title":"Spotem: Efficient video search for episodic memory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramakrishnan","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref76","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11347530.pdf?arnumber=11347530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:10Z","timestamp":1775505370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11347530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":78,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3653482","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":[[2026,5]]}}}