{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:04Z","timestamp":1777889104217,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","award":["PE00000013"],"award-info":[{"award-number":["PE00000013"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01847","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19862-19871","source":"Crossref","is-referenced-by-count":0,"title":["HiERO: Understanding the Hierarchy of Human Behavior Enhances Reasoning on Egocentric Videos"],"prefix":"10.1109","author":[{"given":"Simone Alberto","family":"Peirone","sequence":"first","affiliation":[{"name":"Politecnico di Torino"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesca","family":"Pistilli","sequence":"additional","affiliation":[{"name":"Politecnico di Torino"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Averta","sequence":"additional","affiliation":[{"name":"Politecnico di Torino"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2188"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02209"},{"key":"ref3","article-title":"Video-mined task graphs for keystep recognition in instructional videos","author":"Ashutosh","year":"2023","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_38"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00638"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.08.011"},{"key":"ref8","article-title":"Opel: Optimal transport guided procedure learning","author":"Chowdhury","year":"2024","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.113.4.887"},{"key":"ref10","author":"De la Torre","year":"2008","journal-title":"Carnegie mellon university multimodal activity (cmu-mmac) database"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01817"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_33"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3081010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01723"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00547"},{"key":"ref21","article-title":"Egotaskqa: Understanding human tasks in egocentric videos","author":"Jia","year":"2022","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3462291"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01954"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01083"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref28","article-title":"Egocentric video-language pretraining","author":"Qinghong Lin","year":"2022","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref30","article-title":"Egoschema: A diagnostic benchmark for very longform video language understanding","author":"Mangalam","year":"2023","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01395"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00818"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00878"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"ref35","article-title":"Procedure completion by learning from partial summaries","volume-title":"BMVC","author":"Naing","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01730"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3621326"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01340"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103764"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00771"},{"key":"ref42","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01107"},{"key":"ref44","article-title":"Differentiable task graph learning: Procedural activity representation and online mistake detection from egocentric videos","author":"Seminara","year":"2024","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01722"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref47","article-title":"Ego4d goal-step: Toward hierarchical understanding of procedural activities","author":"Song","year":"2024","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref49","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"NeurIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00484"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02147"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305122"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01424"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01033"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00365"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444628.pdf?arnumber=11444628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:54Z","timestamp":1777612014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01847","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}