{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:33:24Z","timestamp":1761896004758,"version":"build-2065373602"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208902","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Visual-Textual Feature Learning for Rare Human-Object Interactions Detection"],"prefix":"10.1109","author":[{"given":"Mingliang","family":"Xue","sequence":"first","affiliation":[{"name":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Cao","sequence":"additional","affiliation":[{"name":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Duan","sequence":"additional","affiliation":[{"name":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu","family":"Cao","sequence":"additional","affiliation":[{"name":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331738"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref8","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688344"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27949"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3265879"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680927"},{"article-title":"Boosting human-object interaction detection with text-to-image diffusion model","year":"2023","author":"Yang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00912"},{"key":"ref20","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Ross","year":"2017","journal-title":"proceedings of the IEEE conference on computer vision and pattern recognition"},{"article-title":"Visual semantic role labeling","year":"2015","author":"Gupta","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref24"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208902.pdf?arnumber=11208902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:04:17Z","timestamp":1761890657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208902\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208902","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}