{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:32:45Z","timestamp":1773376365903,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794390","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"238-242","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Can Vision Language Models Zero-Shot Thermal Images for Private and Robust Human Robot Interaction?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6777-0616","authenticated-orcid":false,"given":"Han","family":"Hu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8886-9680","authenticated-orcid":false,"given":"He","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"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":"10.3390\/electronics11071151"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN53752.2022.9900548"},{"key":"e_1_3_2_1_3_1","unstructured":"Shuai Bai Yuxuan Cai Ruizhe Chen Keqin Chen Xionghui Chen Zesen Cheng Lianghao Deng Wei Ding Chang Gao Chunjiang Ge et al. 2025. Qwen3-VL Technical Report. arXiv preprint arXiv:2511.21631."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2726356"},{"key":"e_1_3_2_1_5_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv preprint arXiv:2507.06261."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3161198"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/FMSys62467.2024.00011"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICARM62033.2024.10715872"},{"key":"e_1_3_2_1_9_1","unstructured":"Mehdi Moshtaghi Siavash H Khajavi and Joni Pajarinen. 2025. RGB-Th-Bench: a dense benchmark for visual-thermal understanding of vision language models. arXiv preprint arXiv:2503.19654."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3716553.3750767"},{"key":"e_1_3_2_1_11_1","volume-title":"Antonio Paolillo, et al.","author":"Scholz Constantin","year":"2024","unstructured":"Constantin Scholz, Hoang-Long Cao, Emil Imrith, Nima Roshandel, Hamed Firouzipouyaei, Aleksander Burkiewicz, Milan Amighi, Sebastien Menet, Dylan Warawout Sisavath, Antonio Paolillo, et al. 2024. Sensor-enabled safety systems for human-robot collaboration: A review. IEEE Sensors Journal."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.532279"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3371382.3378342"},{"key":"e_1_3_2_1_14_1","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Yuan Dongsheng","unstructured":"Dongsheng Yuan, Xie Zhang, Weiying Hou, Sheng Lyu, Yuemin Yu, Luca Jiang-Tao Yu, Chengxiao Li, and Chenshu Wu. [n. d.]. OctoNet: a large-Scale multi-modal dataset for human activity understanding grounded in motion-captured 3D pose labels. In The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1291682"}],"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":"2026-03-12T20:11:38Z","timestamp":1773346298000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794390"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":15,"alternative-id":["10.1145\/3776734.3794390","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794390","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"}}]}}