{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T18:02:17Z","timestamp":1751997737572,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3481499","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T18:04:50Z","timestamp":1729101890000},"page":"154467-154481","source":"Crossref","is-referenced-by-count":1,"title":["Model Semantic Attention (SemAtt) With Hybrid Learning Separable Neural Network and Long Short-Term Memory to Generate Caption"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8435-7522","authenticated-orcid":false,"given":"Agus","family":"Nursikuwagus","sequence":"first","affiliation":[{"name":"Faculty of Engineering and Computer Science, Universitas Komputer Indonesia, Bandung, Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rinaldi","family":"Munir","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Informatics, Bandung Institute of Technology, Bandung, Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayu L.","family":"Khodra","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Informatics, Bandung Institute of Technology, Bandung, Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1488-7696","authenticated-orcid":false,"given":"Deshinta Arrova","family":"Dewi","sequence":"additional","affiliation":[{"name":"Faculty of Data Science and Information Technology, INTI International University, Nilai, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2598339"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.041"},{"key":"ref3","article-title":"Image captioning","author":"Mullachery","year":"2018","journal-title":"arXiv:1805.09137"},{"key":"ref4","article-title":"Neural image captioning","author":"Tan","year":"2019","journal-title":"arXiv:1907.02065"},{"key":"ref5","first-page":"1","article-title":"Learning CNN-LSTM architectures for image caption generation","author":"Soh","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref8","first-page":"421","article-title":"Joint learning of CNN and LSTM for image captioning","volume-title":"Proc. CEUR Workshop","author":"Zhu"},{"key":"ref9","first-page":"1","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref10","first-page":"345","article-title":"Identifying rock thin section based on convolutional neural networks","volume-title":"Proceedings 9th Int. Workshop Comput. Sci. Eng. (WCSE)","volume":"52","author":"Ren"},{"key":"ref11","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref12","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref13","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref15","first-page":"1","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kaiming"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IC3.2019.8844921"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref18","first-page":"793","article-title":"Image cationing with visual-semantic LSTM","volume-title":"Proc. 27th Int. Joint Conf. Artif. Intell.","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1166"},{"key":"ref20","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref21","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","volume-title":"Proc. ICLR","author":"Junhua"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","first-page":"34","article-title":"ViLBERTScore: Evaluating image caption using vision-and-language BERT","volume-title":"Proc. 1st Workshop Eval. Comparison NLP Syst. (Eval4NLP)","author":"Lee"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app9163260"},{"key":"ref25","article-title":"Image captioning through image transformer","author":"He","year":"2020","journal-title":"arXiv:2004.14231"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12793"},{"key":"ref29","first-page":"1800","article-title":"Xception: Deep learning with depthwise separable convolutions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Chollet"},{"article-title":"Penelitian geologi dan geofisika untuk pengusulan wilayah kerja migas seram onshore","year":"2017","author":"Joko","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref32","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics (ACL)","author":"Papineni"},{"key":"ref33","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","volume":"29","author":"Banerjee"},{"journal-title":"ROUGE: A Package for Automatic Evaluation of Summaries","year":"2004","author":"Lin","key":"ref34"},{"issue":"11","key":"ref35","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/math7080755"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/sym10010011"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/s19183914"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"key":"ref40","first-page":"111","article-title":"A theoretical analysis of feature pooling in visual recognition","volume-title":"Proc. 27th Int. Conf. Mach. Learn.","author":"Boureau"},{"key":"ref41","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. 1st Int. Conf. Learn. Represent. (ICLR)","author":"Mikolov"},{"key":"ref42","article-title":"Understanding LSTM\u2014A tutorial into long short-term memory recurrent neural networks","author":"Staudemeyer","year":"2019","journal-title":"arXiv:1909.09586"},{"key":"ref43","first-page":"1","article-title":"VL-BERT: Pretraining of generic visual","volume-title":"Proc. ICLR","author":"Weijie"},{"issue":"10","key":"ref44","first-page":"567","article-title":"Image captioning using transformer: Visionaid","volume":"9","author":"Shivhare","year":"2022","journal-title":"Int. Res. J. Eng. Tech."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2023.036205"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2023.0140349"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2023.0140973"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10719978.pdf?arnumber=10719978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:51:51Z","timestamp":1732668711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10719978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3481499","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}