{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:32:56Z","timestamp":1773376376572,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","funder":[{"name":"Bijzonder Onderzoeksfonds","award":["BOF22\/DOC\/235"],"award-info":[{"award-number":["BOF22\/DOC\/235"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794486","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"701-705","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Seeing Only When Needed: A Multimodal Architecture for Context-Aware Social Dialogue"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1969-8395","authenticated-orcid":false,"given":"Maria Jose","family":"Pinto Bernal","sequence":"first","affiliation":[{"name":"Ghent University, Ghent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5207-7745","authenticated-orcid":false,"given":"Tony","family":"Belpaeme","sequence":"additional","affiliation":[{"name":"Ghent University, Ghent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10973830"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.1995.7.1.66"},{"key":"e_1_3_2_1_3_1","volume-title":"Embodied conversational agents: representation and intelligence in user interfaces. AI magazine, 22, 4","author":"Cassell Justine","year":"2001","unstructured":"Justine Cassell. 2001. Embodied conversational agents: representation and intelligence in user interfaces. AI magazine, 22, 4 (2001), 67\u201367."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00262"},{"key":"e_1_3_2_1_5_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al. 2023. Palm-e: An embodied multimodal language model."},{"key":"e_1_3_2_1_6_1","volume-title":"Multimodal-gpt: A vision and language model for dialogue with humans. arXiv preprint arXiv:2305.04790.","author":"Gong Tao","year":"2023","unstructured":"Tao Gong, Chengqi Lyu, Shilong Zhang, Yudong Wang, Miao Zheng, Qian Zhao, Kuikun Liu, Wenwei Zhang, Ping Luo, and Kai Chen. 2023. Multimodal-gpt: A vision and language model for dialogue with humans. arXiv preprint arXiv:2305.04790."},{"key":"e_1_3_2_1_7_1","volume-title":"Eye movements in natural behavior. Trends in cognitive sciences, 9, 4","author":"Hayhoe Mary","year":"2005","unstructured":"Mary Hayhoe and Dana Ballard. 2005. Eye movements in natural behavior. Trends in cognitive sciences, 9, 4 (2005), 188\u2013194."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3428704"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00147"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731379"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3716553.3750767"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Federico Rossano. 2012. Gaze in conversation. The handbook of conversation analysis 308\u2013329.","DOI":"10.1002\/9781118325001.ch15"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Kazuhiro Sasabuchi Naoki Wake Atsushi Kanehira Jun Takamatsu and Katsushi Ikeuchi. 2025. Agreeing to interact in human-robot interaction using large language models and vision language models. arXiv preprint arXiv:2503.15491.","DOI":"10.1109\/RO-MAN63969.2025.11217646"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.uncertainlp-main.10"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15327973rlsi3904_2"},{"key":"e_1_3_2_1_18_1","unstructured":"Yiyang Zhou Chenhang Cui Jaehong Yoon Linjun Zhang Zhun Deng Chelsea Finn Mohit Bansal and Huaxiu Yao. 2023. Analyzing and mitigating object hallucination in large vision-language models. arXiv preprint arXiv:2310.00754."}],"event":{"name":"HRI '26: 21st ACM\/IEEE International Conference on Human-Robot Interaction","location":"Edinburgh Scotland UK","acronym":"HRI '26","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction","IEEE RAS"]},"container-title":["Companion Proceedings of the 21st ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:12:04Z","timestamp":1773346324000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":18,"alternative-id":["10.1145\/3776734.3794486","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794486","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"2026-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}