{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:42:53Z","timestamp":1772905373549,"version":"3.50.1"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["NRF-NRFFAI1-2019-0001"],"award-info":[{"award-number":["NRF-NRFFAI1-2019-0001"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3218596","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:38:33Z","timestamp":1667525913000},"page":"7836-7852","source":"Crossref","is-referenced-by-count":15,"title":["Transferring Knowledge From Text to Video: Zero-Shot Anticipation for Procedural Actions"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5004-6005","authenticated-orcid":false,"given":"Fadime","family":"Sener","sequence":"first","affiliation":[{"name":"University of Bonn, Bonn, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7830-423X","authenticated-orcid":false,"given":"Rishabh","family":"Saraf","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology (ISM) Dhanbad, Dhanbad, Jharkhand, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.17"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref59","article-title":"Action2Vec: A crossmodal embedding approach to action learning","author":"hahn","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00983"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref54","article-title":"Prediction and description of near-future activities in video","author":"mahmud","year":"2020"},{"key":"ref51","article-title":"Egocentric object manipulation graphs","author":"dessalene","year":"2020"},{"key":"ref50","first-page":"704","article-title":"Forecasting human object interaction: Joint prediction of motor attention and egocentric activity","author":"liu","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref46","article-title":"Learning representations for predicting future activities","author":"zolfaghari","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref48","article-title":"Knowledge distillation for action anticipation via label smoothing","author":"camporese","year":"2020"},{"key":"ref47","article-title":"Back to the future: Knowledge distillation for human action anticipation","author":"tran","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.616"},{"key":"ref43","article-title":"Rescaling egocentric vision","author":"damen","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref3","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"2017","journal-title":"Proc Conf Robot Learn"},{"key":"ref6","article-title":"How to do anything","year":"2005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref100","article-title":"Speech understanding systems. Summary of results of the five-year research effort at Carnegie-Mellon University","year":"1977"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3207"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00351"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.509"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00366"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.140"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01234"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00873"},{"key":"ref24","first-page":"753","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01070"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00095"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref22","article-title":"Generating multi-sentence lingual descriptions of indoor scenes","author":"lin","year":"2015","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.511"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995470"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"ref13","first-page":"2231","article-title":"Multimodal learning with deep Boltzmann machines","author":"srivastava","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref12","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref97","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-2407"},{"key":"ref99","article-title":"The curious case of neural text degeneration","author":"holtzman","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"ref98","article-title":"Natural language toolkit","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref93","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/1380584.1380586"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1230"},{"key":"ref94","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref90","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref89","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref86","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1162"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1070"},{"key":"ref82","article-title":"Decomposed generation networks with structure prediction for recipe generation from food images","author":"wang","year":"2020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"ref84","article-title":"A neural conversational model","author":"vinyals","year":"2015","journal-title":"Proc Int Conf Mach Learn Deep Learn Workshop"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01184"},{"key":"ref79","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.440"},{"key":"ref104","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref74","first-page":"181","article-title":"RecipeGPT: Generative pre-training based cooking recipe generation and evaluation system","author":"lee","year":"2020","journal-title":"Proc Companion Proc Web Conf"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487401"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1032"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100855"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1016"},{"key":"ref72","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1114"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509955"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1090"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210036"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123272"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/981623.981632"},{"key":"ref65","first-page":"267","article-title":"CHEF: A model of case-based planning","author":"hammond","year":"1986","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref62","article-title":"Food recognition and recipe analysis: Integrating visual content, context and external knowledge","author":"herranz","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09933901.pdf?arnumber=9933901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:35:22Z","timestamp":1685381722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9933901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":104,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3218596","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":[[2023,6,1]]}}}