{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T13:36:32Z","timestamp":1769607392494,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"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":[[2023,11,27]]},"DOI":"10.1109\/iccais59597.2023.10382370","type":"proceedings-article","created":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T19:38:20Z","timestamp":1704915500000},"page":"212-217","source":"Crossref","is-referenced-by-count":2,"title":["Performance Evaluation of CNN-based Encoders for Image Captioning"],"prefix":"10.1109","author":[{"given":"Anh Cong","family":"Hoang","sequence":"first","affiliation":[{"name":"Thanh Hoa University of Culture, Sports and Tourism,Thanh Hoa,Viet Nam"}]},{"given":"Dinh Cong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Hong Duc University,Thanh Hoa,Viet Nam"}]},{"given":"Hoang Long","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Hong Duc University,Thanh Hoa,Viet Nam"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"arXiv preprint arXiv:1409.0473","author":"Bahdanau"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2018.00063"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3177745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref13","article-title":"Convnext-backbone hovernet for nuclei segmentation and classification","author":"Li","year":"2022","journal-title":"arXiv preprint arXiv:2202.13560"},{"key":"ref14","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","volume-title":"In Conference on computational natural language learning","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"Mao","year":"2014","journal-title":"arXiv preprint arXiv:1412.6632"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref19","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"ANIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref21","volume-title":"Image captioning using an lstm network","author":"Rungta"},{"key":"ref22","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"In ICML","author":"Tan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref24","article-title":"Image captioning and visual question answering based on attributes and their related external knowledge","volume":"2","author":"Wu","year":"2016","journal-title":"arXiv preprint arXiv:1603.02814"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2915033"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref28","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"In ICML","author":"Xu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref31","article-title":"Dive into deep learning","author":"Zhang","year":"2021","journal-title":"arXiv preprint arXiv:2106.11342"}],"event":{"name":"2023 12th International Conference on Control, Automation and Information Sciences (ICCAIS)","location":"Hanoi, Vietnam","start":{"date-parts":[[2023,11,27]]},"end":{"date-parts":[[2023,11,29]]}},"container-title":["2023 12th International Conference on Control, Automation and Information Sciences (ICCAIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10382256\/10382242\/10382370.pdf?arnumber=10382370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T18:23:35Z","timestamp":1705170215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iccais59597.2023.10382370","relation":{},"subject":[],"published":{"date-parts":[[2023,11,27]]}}}