{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T09:36:22Z","timestamp":1761989782654,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["62376217","62301434"],"award-info":[{"award-number":["62376217","62301434"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]},{"name":"Key Research and Development Project of Shaanxi Province","award":["2023-YBGY-240"],"award-info":[{"award-number":["2023-YBGY-240"]}]},{"name":"Young Talent Fund of Association for Science and Technology in Shaanxi, China","award":["20220117"],"award-info":[{"award-number":["20220117"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3425598","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T19:01:44Z","timestamp":1720551704000},"page":"11605-11618","source":"Crossref","is-referenced-by-count":8,"title":["VS-TransGRU: A Novel Transformer-GRU-Based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0217-9791","authenticated-orcid":false,"given":"Congqi","family":"Cao","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"given":"Ze","family":"Sun","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5359-5701","authenticated-orcid":false,"given":"Qinyi","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3970-7823","authenticated-orcid":false,"given":"Lingtong","family":"Min","sequence":"additional","affiliation":[{"name":"School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pedestrian action anticipation using contextual feature fusion in stacked RNNs","author":"Rasouli","year":"2020","journal-title":"arXiv:2005.06582"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016120"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref4","first-page":"295","article-title":"Robot-centric activity prediction from first-person videos: What will they do to me?","volume-title":"Proc. 10th ACM\/IEEE Int. Conf. Human-Robot Interact. (HRI)","author":"Ryoo"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2976789"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3137023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077512"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992889"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01353"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040521"},{"key":"ref15","article-title":"Higher order recurrent space-time transformer for video action prediction","author":"Tai","year":"2021","journal-title":"arXiv:2104.08665"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956467"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00306"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00383"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71278-5_12"},{"key":"ref24","article-title":"Forecasting future action sequences with neural memory networks","author":"Gammulle","year":"2019","journal-title":"arXiv:1909.09278"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00270"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01302"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01240"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00254"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475327"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00088"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00601"},{"key":"ref37","first-page":"720","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Damen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00660"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00846"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.846"},{"key":"ref46","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_24"},{"key":"ref50","article-title":"Smooth loss functions for deep top-k classification","author":"Berrada","year":"2018","journal-title":"arXiv:1802.07595"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00173"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28442"},{"key":"ref56","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Bergstra"},{"key":"ref57","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv:1803.01271"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412660"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3633333"},{"key":"ref60","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768851\/10589709.pdf?arnumber=10589709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:55:00Z","timestamp":1732697700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10589709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":60,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3425598","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}