{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:22:15Z","timestamp":1782220935507,"version":"3.54.5"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447637","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4290-4294","source":"Crossref","is-referenced-by-count":7,"title":["Improved Image Captioning Via Knowledge Graph-Augmented Models"],"prefix":"10.1109","author":[{"given":"Sergio S\u00e1nchez","family":"Santiesteban","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Atito","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Awais","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Programs with common sense","author":"McCarthy","year":"1960"},{"key":"ref2","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00036"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16796"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref6","article-title":"Sit: Self-supervised vision transformer","author":"Atito","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref9","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"ICML","author":"Kim"},{"key":"ref10","article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","author":"Dou","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref14","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref15","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2019"},{"key":"ref16","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref19","first-page":"54","article-title":"Flair: An easy-to-use framework for state-of-the-art nlp","author":"Akbik","year":"2019","journal-title":"ACL 2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref22","article-title":"CPTR: Full Transformer Network for Image Captioning","author":"Liu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref24","article-title":"Microsoft COCO Captions: Data Collection and Evaluation Server","author":"Chen","year":"2015"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.3115\/1073083.1073135","article-title":"Bleu: a Method for Automatic Evaluation of Machine Translation","volume-title":"40th ACL","author":"Papineni"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref27","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries","author":"Lin","year":"2004"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447637.pdf?arnumber=10447637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:53:52Z","timestamp":1722578032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447637","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}