{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:24:43Z","timestamp":1746678283814,"version":"3.28.0"},"reference-count":28,"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\/icasspw59220.2023.10193011","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Glove-Ing Attention: A Multi-Modal Neural Learning Approach to Image Captioning"],"prefix":"10.1109","author":[{"given":"Lars Halvor","family":"Anundsk\u00e5s","sequence":"first","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Computer Science,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hina","family":"Afridi","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Computer Science,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adane Nega","family":"Tarekegn","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Computer Science,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Mudassar","family":"Yamin","sequence":"additional","affiliation":[{"name":"CUI Wah Campus, Wah Cantt,Department of Management Sciences,Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohib","family":"Ullah","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Computer Science,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saira","family":"Yamin","sequence":"additional","affiliation":[{"name":"CUI Wah Campus, Wah Cantt,Department of Management Sciences,Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faouzi Alaya","family":"Cheikh","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Computer Science,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43823-4_35"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325049"},{"journal-title":"Learn to combine modalities in multimodal deep learning","year":"2018","author":"liu","key":"ref15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/sym12122010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102097"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975036"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iCoMET57998.2023.10099311"},{"key":"ref1","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"3","author":"xu","year":"2015","journal-title":"32nd International Conference on Machine Learning ICML 2015"},{"key":"ref17","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"4","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref19","first-page":"10691","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"2019","author":"tan","year":"2019","journal-title":"36th International Conference on Machine Learning ICML 2019"},{"key":"ref18","first-page":"3156","article-title":"Show and tell: A neural image caption generator","volume":"7 12 june","author":"vinyals","year":"2015","journal-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.026"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"30615","DOI":"10.1007\/s11042-020-09539-5","article-title":"Reference-based model using multimodal gated recurrent units for image captioning","volume":"79","author":"tiago","year":"2020","journal-title":"Multimedia Tools and Applications"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5856-1"},{"key":"ref25","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"13th European Conference on Computer Vision"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jamia\/ocv080","article-title":"Preparing a collection of radiology examinations for distribution and retrieval","volume":"23","author":"dina","year":"2016","journal-title":"Journal of the American Medical Informatics Association"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.288"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32692-0_77"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.10.059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025814"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3545572"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2352\/EI.2023.35.1.VDA-407"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3384\/ecp187043"},{"key":"ref3","article-title":"Memorial gan with joint semantic optimization for unpaired image captioning","author":"song","year":"2022","journal-title":"IEEE Transactions on Cybernetics"},{"key":"ref6","article-title":"Text with knowledge graph augmented transformer for video captioning","author":"gu","year":"2023","journal-title":"arXiv preprint arXiv 2303 12423"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193011.pdf?arnumber=10193011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:38Z","timestamp":1692639758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193011\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193011","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}