{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:13:13Z","timestamp":1755839593077,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/icme55011.2023.00032","type":"proceedings-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T17:18:08Z","timestamp":1692983888000},"page":"138-143","source":"Crossref","is-referenced-by-count":3,"title":["Scene Graph based Fusion Network for Image-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Guoliang","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Institute of Network Technology,Beijing,China"}]},{"given":"Yanlei","family":"Shang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Institute of Network Technology,Beijing,China"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Institute of Network Technology,Beijing,China"}]},{"given":"Chaoqi","family":"Zhen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Institute of Network Technology,Beijing,China"}]},{"given":"Dequan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Institute of Network Technology,Beijing,China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.3233\/FAIA210049"},{"key":"ref24","article-title":"Deepvit: Towards deeper vision transformer","author":"zhou","year":"2021","journal-title":"CVPR"},{"key":"ref12","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume":"34","author":"nagrani","year":"2021","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR42600.2020.00359"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV.2015.303"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/3459637.3482218"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR42600.2020.01095"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR52688.2022.01516"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR52688.2022.01521"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/WACV51458.2022.00252"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/3343031.3350940"},{"year":"2022","author":"cong","article-title":"Reltr: Relation transformer for scene graph generation","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","article-title":"Learning two-branch neural networks for image-text matching tasks","volume":"41","author":"wang","year":"2018","journal-title":"TPAMI"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.24963\/ijcai.2019\/526"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref8","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref7","article-title":"Multi-scale fine-grained alignments for image and sentence matching","author":"li","year":"2021","journal-title":"IEEE Trans Multimedia"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR42600.2020.01093"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.24963\/ijcai.2021\/106"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref6","article-title":"Vision-language intelligence: Tasks, representation learning, and large models","author":"li","year":"2022","journal-title":"ArXiv"},{"key":"ref5","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"2018","journal-title":"ECCV"}],"event":{"name":"2023 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2023,7,10]]},"location":"Brisbane, Australia","end":{"date-parts":[[2023,7,14]]}},"container-title":["2023 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10219544\/10219545\/10219578.pdf?arnumber=10219578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T17:41:59Z","timestamp":1695058919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10219578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme55011.2023.00032","relation":{},"subject":[],"published":{"date-parts":[[2023,7]]}}}