{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:29:00Z","timestamp":1761895740921,"version":"build-2065373602"},"reference-count":29,"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\/icme59968.2025.11209235","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 Relationships Are Different: Appropriate Way To Predict Each Relationship"],"prefix":"10.1109","author":[{"given":"Zhenhua","family":"Lei","sequence":"first","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuemei","family":"Xie","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28098"},{"key":"ref2","article-title":"Zero-shot visual relation detection via composite visual cues from large language models","volume-title":"NIPS","volume":"36","author":"Li"},{"key":"ref3","article-title":"Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering","volume-title":"NIPS","volume":"36","author":"Lin"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350962"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"ref11","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"NeuralPS"},{"article-title":"Exploring the hierarchy in relation labels for scene graph generation","year":"2020","author":"Zhou","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413722"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01884"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25435"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105572"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02675"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01180"}],"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\/11209235.pdf?arnumber=11209235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:58:07Z","timestamp":1761890287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209235","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}