{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:43Z","timestamp":1763190823246,"version":"3.45.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228320","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["HierADL: Automatic Hierarchical Structures to Improve Daily Activity Recognition"],"prefix":"10.1109","author":[{"given":"Manuel","family":"Benavent-Lledo","sequence":"first","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Ortiz-Perez","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Mulero-Perez","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Ruiz-Ponce","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Garcia-Rodriguez","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2020.05.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01084"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00803"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3148431"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.05.027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00161"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341160"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104560"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3169976"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00470"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.118"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"article-title":"Vision transformers for action recognition: A survey","year":"2022","author":"Ulhaq","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"article-title":"Actionclip: A new paradigm for video action recognition","year":"2021","author":"Wang","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01242"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222914"},{"article-title":"Antgpt: Can large language models help long-term action anticipation from videos?","volume-title":"ICLR","author":"Zhao","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02209"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32751"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534447"},{"article-title":"Large language models: A survey","year":"2024","author":"Minaee","key":"ref43"},{"article-title":"Gpt-4 technical report","year":"2024","author":"Achiam","key":"ref44"},{"article-title":"The llama 3 herd of models","year":"2024","author":"Grattafiori","key":"ref45"},{"article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","year":"2024","author":"Georgiev","key":"ref46"},{"article-title":"Dinov2: Learning robust visual features without supervision","year":"2024","author":"Oquab","key":"ref47"},{"key":"ref48","first-page":"10 078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Advances in neural information processing systems","volume":"35","author":"Tong"},{"article-title":"Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter","year":"2019","author":"Sanh","key":"ref49"},{"article-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref50"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228320.pdf?arnumber=11228320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:12:00Z","timestamp":1763190720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228320","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}