{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:59:33Z","timestamp":1783529973147,"version":"3.55.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888344","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Visual Captions for Enhanced Zero-Shot HOI Detection"],"prefix":"10.1109","author":[{"given":"Yanqing","family":"Zeng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,EEIS Department,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyao","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,EEIS Department,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenbo","family":"Lu","sequence":"additional","affiliation":[{"name":"Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,EEIS Department,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,EEIS Department,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/MVA57639.2023.10215534"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446505"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref10","article-title":"ican: Instance-centric attention network for human-object interaction detection","volume-title":"Proceedings of the British Machine Vision Conference","author":"Gao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20041"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00093"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446756"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_27"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01441"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447601"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref23","first-page":"45895","article-title":"Clip4hoi: Towards adapting clip for practical zero-shot hoi detection","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"36","author":"Mao"},{"key":"ref24","article-title":"Detecting any human-object interaction relationship: Universal hoi detector with spatial prompt learning on foundation models","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"36","author":"Cao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27949"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref28","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015"},{"key":"ref29","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref33","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref34","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref35","first-page":"37416","article-title":"Rlip: Relational language-image pre-training for human-object interaction detection","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"35","author":"Yuan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref38","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage hoi detection","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"34","author":"Zhang"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888344.pdf?arnumber=10888344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:54Z","timestamp":1774416174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888344","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}