{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:40:13Z","timestamp":1734982813610,"version":"3.32.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"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":[[2024,10,18]]},"DOI":"10.1109\/mlnlp63328.2024.10800032","type":"proceedings-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T18:56:07Z","timestamp":1734720967000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["VTN-EG: CLIP-Based Visual and Textual Fusion Network for Entity Grounding"],"prefix":"10.1109","author":[{"given":"Shiyi","family":"Hao","sequence":"first","affiliation":[{"name":"Center for Space Utilization, Chinese Academy of Sciences,Technology and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Space Utilization, Chinese Academy of Sciences,Technology and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Center for Space Utilization, Chinese Academy of Sciences,Technology and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Space Utilization, Chinese Academy of Sciences,Technology and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Center for Space Utilization, Chinese Academy of Sciences,Technology and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengyang","family":"Li","sequence":"additional","affiliation":[{"name":"Center for Space Utilization, Chinese Academy of Sciences,Technology and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"16","key":"ref1","article-title":"Introducing the knowledge graph: things, not strings[J]","volume":"5","author":"Singhal","year":"2012","journal-title":"Official google blog"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450133"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3055371"},{"key":"ref4","first-page":"279","article-title":"European Semantic Web Conference","volume-title":"Gett-qa: Graph embedding based t2t transformer for knowledge graph question answering[C]","author":"Banerjee","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3224228"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision[C]","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref7","article-title":"Answering visual-relational queries in web-extracted knowledge graphs[J]","author":"O\u00f1oro-Rubio","year":"2017","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933370"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2020.100159"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrl-1.13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2012.07.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612266"},{"key":"ref15","first-page":"18","article-title":"Mmpedia: A large-scale multimodal knowledge graph[C]","volume-title":"International Semantic Web Conference","author":"Wu","year":"2023"},{"key":"ref16","first-page":"779","article-title":"You only look once: Uni-fied, real-time object detection[C]","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Redmon","year":"2016"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition[J]","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614782"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref23","first-page":"249","article-title":"Understanding the difficulty of training deep feed-forward neural networks[C]","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Glorot","year":"2010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref25","article-title":"Fine-grained visual classification of aircraft[J]","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2024 7th International Conference on Machine Learning and Natural Language Processing (MLNLP)","start":{"date-parts":[[2024,10,18]]},"location":"Chengdu, China","end":{"date-parts":[[2024,10,20]]}},"container-title":["2024 7th International Conference on Machine Learning and Natural Language Processing (MLNLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799945\/10799990\/10800032.pdf?arnumber=10800032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:07Z","timestamp":1734981067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,18]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/mlnlp63328.2024.10800032","relation":{},"subject":[],"published":{"date-parts":[[2024,10,18]]}}}