{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T07:45:50Z","timestamp":1767771950484,"version":"3.29.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"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":[[2024,8,26]]},"DOI":"10.1109\/ro-man60168.2024.10731447","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:45:45Z","timestamp":1730310345000},"page":"740-747","source":"Crossref","is-referenced-by-count":1,"title":["Improving Learning from Visual Demonstration Methods by Target Localization"],"prefix":"10.1109","author":[{"given":"Pasquale","family":"Foggia","sequence":"first","affiliation":[{"name":"University of Salerno,Department of Information and Electrical Engineering and Applied Mathematics,Italy"}]},{"given":"Francesco","family":"Rosa","sequence":"additional","affiliation":[{"name":"University of Salerno,Department of Information and Electrical Engineering and Applied Mathematics,Italy"}]},{"given":"Mario","family":"Vento","sequence":"additional","affiliation":[{"name":"University of Salerno,Department of Information and Electrical Engineering and Applied Mathematics,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05204-1_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref3","first-page":"1","article-title":"Identity, gender, age, and emotion recognition from speaker voice with multitask deep networks for cognitive robotics","author":"Foggia","year":"2024","journal-title":"Cognitive Computation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.10.022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812450"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160944"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref8","first-page":"2071","article-title":"Transformers for one-shot visual imitation","volume-title":"Proceedings of the 2020 Conference on Robot Learning","volume":"155","author":"Dasari"},{"key":"ref9","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proceedings of the 5th Conference on Robot Learning","volume":"164","author":"Jang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref12","article-title":"Probabilistic movement primitives","volume-title":"Advances in Neural Information Processing Systems","volume":"26","author":"Paraschos"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9706-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3009063"},{"key":"ref15","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Proceedings of the 5th Conference on Robot Learning","volume":"164","author":"Mandlekar"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00357"},{"key":"ref17","first-page":"892","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref19","first-page":"13139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Stepputtis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref21","first-page":"785","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)","author":"Shridhar","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref25","first-page":"783","article-title":"Task-embedded control networks for few-shot imitation learning","volume-title":"Conference on robot learning","author":"James"},{"key":"ref26","first-page":"11261135","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461196"},{"key":"ref28","first-page":"3029","article-title":"Objectaware regularization for addressing causal confusion in imitation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Park"},{"key":"ref29","first-page":"1199","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Zhu"},{"article-title":"Learning generalizable manipulation policies with object-centric 3d representations","volume-title":"7th Annual Conference on Robot Learning","author":"Zhu","key":"ref30"},{"article-title":"Vima: General robot manipulation with multimodal prompts","volume-title":"NeurIPS 2022 Foundation Models for Decision Making Workshop","author":"Jiang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.31979\/etd.8zhj-5qdc"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref39","article-title":"Faster r-cnn: Towards realtime object detection with region proposal networks","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Ren"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref40"},{"article-title":"robosuite: A modular simulation framework and benchmark for robot learning","year":"2020","author":"Zhu","key":"ref41"},{"article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref42"}],"event":{"name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","start":{"date-parts":[[2024,8,26]]},"location":"Pasadena, CA, USA","end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10731142\/10731137\/10731447.pdf?arnumber=10731447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T04:24:26Z","timestamp":1732681466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10731447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ro-man60168.2024.10731447","relation":{},"subject":[],"published":{"date-parts":[[2024,8,26]]}}}