{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:53:26Z","timestamp":1730249606911,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859926","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T15:45:18Z","timestamp":1661528718000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Relational Graph Reasoning Transformer for Image Captioning"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Xiao","sequence":"first","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingtian","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yipeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"203","article-title":"What value do explicit high level concepts have in vision to language problems?","author":"qi","year":"0","journal-title":"CVPR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"ACL"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219947"},{"key":"ref14","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"lin","year":"0","journal-title":"ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref16","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"0","journal-title":"ACL2 Workshop"},{"key":"ref17","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"0","journal-title":"ACL2 Workshop"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref8","first-page":"11135","article-title":"Image captioning: Transforming objects into words","author":"herdade","year":"0","journal-title":"NeurIPS"},{"key":"ref7","first-page":"711","article-title":"Exploring visual relationship for image captioning","volume":"11218","author":"yao","year":"0","journal-title":"ECCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref9","first-page":"413","article-title":"Videos as space-time region graphs","volume":"11209","author":"wang","year":"2018","journal-title":"ECCV"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref22","first-page":"1655","article-title":"Improving image captioning by leveraging intra- and inter-layer global representation in transformer network","author":"ji","year":"0","journal-title":"AAAI"},{"key":"ref21","first-page":"2584","article-title":"Image captioning with context-aware auxiliary guidance","author":"song","year":"0","journal-title":"AAAI"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859926.pdf?arnumber=9859926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T16:25:01Z","timestamp":1663604701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859926","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}