{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:14:05Z","timestamp":1778080445108,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"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":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217803","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"1151-1158","source":"Crossref","is-referenced-by-count":3,"title":["Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights"],"prefix":"10.1109","author":[{"given":"Yuchen","family":"Liu","sequence":"first","affiliation":[{"name":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lino","family":"Lerch","sequence":"additional","affiliation":[{"name":"Ulm University,Visual Computing Group,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luigi","family":"Palmieri","sequence":"additional","affiliation":[{"name":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Rudenko","sequence":"additional","affiliation":[{"name":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Koch","sequence":"additional","affiliation":[{"name":"Robert Bosch GmbH,Corporate Sector Research and Advance Engineering,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timo","family":"Ropinski","sequence":"additional","affiliation":[{"name":"Ulm University,Visual Computing Group,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Aiello","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Institute of Architecture of Application Systems,Service Computing Department,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920917446"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3281393"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102404"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3461552"},{"key":"ref6","article-title":"Robust human motion prediction for safe and efficient human-robot interaction","volume-title":"Ph.D. dissertation","author":"Lasota","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.05.007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2021.3105977"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127838"},{"key":"ref10","article-title":"Wildhallucinations: Evaluating long-form factuality in llms with real-world entity queries","author":"Zhao","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3627546"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_18"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00036"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN53752.2022.9900656"},{"key":"ref20","article-title":"Challenges of data-driven simulation of diverse and consistent human driving behaviors","author":"Kujanp\u00e4\u00e4","year":"2024"},{"key":"ref21","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. of the European Conf. on computer vision (ECCV)","author":"Damen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_9"},{"key":"ref25","article-title":"Antgpt: Can large language models help long-term action anticipation from videos?","author":"Zhao","year":"2024","journal-title":"ICLR"},{"key":"ref26","article-title":"On the efficacy of text-based input modalities for action anticipation","author":"Beedu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3482169"},{"key":"ref28","article-title":"Towards human awareness in robot task planning with large language models","author":"Liu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611090"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.807"},{"key":"ref31","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. on machine learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref33","article-title":"Hello GPT-4o","year":"2024"},{"key":"ref34","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref35","article-title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","author":"Li","year":"2024"},{"key":"ref36","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Language Models are Few-Shot Learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","first-page":"23 716","article-title":"Flamingo: a Visual Language Model for Few-Shot Learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Eindhoven, Netherlands","start":{"date-parts":[[2025,8,25]]},"end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217803.pdf?arnumber=11217803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:01:25Z","timestamp":1762236085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217803","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}