{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:26:55Z","timestamp":1775665615216,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,22]]},"DOI":"10.1109\/humanoids58906.2024.10769830","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T18:54:29Z","timestamp":1733252069000},"page":"141-148","source":"Crossref","is-referenced-by-count":3,"title":["Diffusing in Someone Else\u2019s Shoes: Robotic Perspective-Taking with Diffusion"],"prefix":"10.1109","author":[{"given":"Josua","family":"Spisak","sequence":"first","affiliation":[{"name":"University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Kerzel","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology (WTM) group,Department of Informatics,Hamburg,Germany,22527"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2013.06.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2013.00698"},{"key":"ref3","article-title":"Embodied Multi-modal Interaction in Language learning: the EMIL data collection","volume-title":"Proceedings of the ICDL-EpiRob Workshop on Active Vision, Attention, and Learning (ICDL-Epirob 2018 AVAL).","author":"Heinrich"},{"key":"ref4","article-title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","author":"Fang","year":"2023","journal-title":"arXiv:2307.00595"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"ref6","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"02502","key":"ref7","article-title":"Denoising diffusion implicit models","volume":"2010","author":"Song","year":"2020"},{"key":"ref8","article-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDL53763.2022.9962214"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref16","first-page":"36479","article-title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00930"},{"key":"ref18","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume-title":"Proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI)","author":"Olaf"},{"key":"ref19","first-page":"785","article-title":"PERCEIVER-ACTOR: A Multi-Task Transformer for Robotic Manipulation","volume-title":"Conference on Robot Learning (CoRL).","volume":"205","author":"Mohit"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004787"},{"key":"ref21","first-page":"38571","article-title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","volume":"35","author":"Xu","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref22","article-title":"Third-Person Imitation Learning","author":"Stadie","year":"2017","journal-title":"arXiv:1703.01703"},{"key":"ref23","first-page":"1990","article-title":"Mirror Perspective-Taking with a Humanoid Robot","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","volume":"26","author":"Hart"},{"key":"ref24","first-page":"8162","article-title":"Improved Denoising Diffusion Probabilistic Models","volume-title":"Proceedings of Machine Learning Research","author":"Nichol"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3329370"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2017.8172289"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13310"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44207-0_38"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-30301-5","volume-title":"Handbook of Robotics.","volume":"200","author":"Siciliano","year":"2008"}],"event":{"name":"2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)","location":"Nancy, France","start":{"date-parts":[[2024,11,22]]},"end":{"date-parts":[[2024,11,24]]}},"container-title":["2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10769770\/10769590\/10769830.pdf?arnumber=10769830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T19:56:20Z","timestamp":1736538980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10769830\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/humanoids58906.2024.10769830","relation":{},"subject":[],"published":{"date-parts":[[2024,11,22]]}}}