{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:05Z","timestamp":1781761865268,"version":"3.54.5"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"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":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11557036","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Towards Unconstrained Human-Object Interaction"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Tonini","sequence":"first","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Conti","sequence":"additional","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Vaquero","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cigdem","family":"Beyan","sequence":"additional","affiliation":[{"name":"University of Verona,Department of Computer Science,Verona,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv preprint arXiv:2404.14219","author":"Abdin","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-025-01330-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0034"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_26"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680927"},{"key":"ref12","article-title":"Measuring mathematical problem solving with the math dataset","volume-title":"arXiv preprint arXiv:2103.03874","author":"Hendrycks"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref14","article-title":"spaCy: Industrial-strength Natural Language Processing in Python","author":"Honnibal","year":"2020"},{"issue":"2","key":"ref15","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref16","article-title":"Visual instruction tuning towards general-purpose multimodal model: A survey","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2312.16602"},{"key":"ref17","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv:2410.21276"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01880"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2789"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_1"},{"key":"ref27","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2408.03326"},{"key":"ref28","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0924"},{"key":"ref30","first-page":"10163","article-title":"Detailed 2d3d joint representation for human-object interaction","volume-title":"IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054048"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413600"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02665"},{"key":"ref42","first-page":"17939","article-title":"Moma: Multi-object multi-actor activity parsing","volume":"34","author":"Luo","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"CLIP4HOI: towards adapting CLIP for practical zero-shot HOI detection","author":"Mao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref44","article-title":"Hoi4abot: Human-object interaction anticipation for human intention reading collaborative robots","volume-title":"7 th Annual Conference on Robot Learning","author":"Mascaro"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref46","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016","journal-title":"CoRR, abs\/1603.00831"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075938"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1349822.1349843"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref56","article-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024","journal-title":"arXiv preprint arXiv:2408.03314"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754770"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref59","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2409.12191"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01687"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28422"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531452"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01604"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680680"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00641"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326279"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01234-9"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11557036.pdf?arnumber=11557036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:52:20Z","timestamp":1781758340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11557036","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}