{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:06:41Z","timestamp":1764842801227,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"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":[[2023,10,26]]},"DOI":"10.1109\/wincom59760.2023.10322923","type":"proceedings-article","created":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T14:07:27Z","timestamp":1700662047000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Evolution of Image Captioning Models: An Overview"],"prefix":"10.1109","author":[{"given":"Abdelkrim","family":"Saouabe","sequence":"first","affiliation":[{"name":"IbnTofail University,Computer Science Research Laboratory, Faculty of Sciences,Kénitra,Morocco"}]},{"given":"Said","family":"Tkatek","sequence":"additional","affiliation":[{"name":"IbnTofail University,Computer Science Research Laboratory, Faculty of Sciences,Kénitra,Morocco"}]},{"given":"Merouane","family":"Mazar","sequence":"additional","affiliation":[{"name":"AKKODIS,Paris,France"}]},{"given":"Imad","family":"Mourtaji","sequence":"additional","affiliation":[{"name":"AKKODIS,Paris,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-1338-8_43"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1803"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/9638438"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/Confluence52989.2022.9734171"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref9","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv preprint arXiv:1411.2539"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2019.107329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5655"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref16","article-title":"Fast sequence generation with multi-agent reinforcement learning","author":"Guo","year":"2021","journal-title":"arXiv preprint arXiv:2101.09698"},{"key":"ref17","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"volume-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref19"},{"key":"ref20","article-title":"Image captioning: Transforming objects into words","volume":"32","author":"Herdade","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref22","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv preprint arXiv:2108.10904"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16249"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18280\/isi.280230"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3268744"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3282444"}],"event":{"name":"2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM)","start":{"date-parts":[[2023,10,26]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2023,10,28]]}},"container-title":["2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10322877\/10322879\/10322923.pdf?arnumber=10322923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T17:07:35Z","timestamp":1703005655000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10322923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/wincom59760.2023.10322923","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]}}}