{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:44:35Z","timestamp":1730231075776,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096823","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Spatial Cross-Attention for Transformer-Based Image Captioning"],"prefix":"10.1109","author":[{"given":"Khoa","family":"Anh Ngo","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyuhong","family":"Shim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byonghyo","family":"Shim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","year":"2020","author":"Iashin","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1246729"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/ELECO47770.2019.8990630"},{"article-title":"Attention is all you need","year":"2017","author":"Vaswani","key":"ref4"},{"article-title":"Cptr: Full transformer network for image captioning","year":"2021","author":"Liu","key":"ref5"},{"article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","year":"2022","author":"Wang","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11060945"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104146"},{"key":"ref10","article-title":"Image captioning: Transforming objects into words","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Herdade","year":"2019"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298932"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299087"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref20","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096823.pdf?arnumber=10096823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:53:22Z","timestamp":1709247202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096823","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}