平衡整体和局部:改进图像字幕与增强变压器模型

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI:10.1109/AINIT59027.2023.10212804

Haotian Xian, Baoyi Guo, Youyu Zhou

{"title":"平衡整体和局部:改进图像字幕与增强变压器模型","authors":"Haotian Xian, Baoyi Guo, Youyu Zhou","doi":"10.1109/AINIT59027.2023.10212804","DOIUrl":null,"url":null,"abstract":"This article proposes a Transformer-based image captioning model using computer vision and natural language processing techniques. The model is based on Multi-Featured Attention Module and Grid-Augmented Module and outperforms the original Transformer model on all evaluation metrics. Specifically, with a beam size of 7, the model achieves a BLEU-4 score of 0.409 and a CIDEr score of 1.008.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Balanced Overall and Local: Improving Image Captioning with Enhanced Transformer Model\",\"authors\":\"Haotian Xian, Baoyi Guo, Youyu Zhou\",\"doi\":\"10.1109/AINIT59027.2023.10212804\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article proposes a Transformer-based image captioning model using computer vision and natural language processing techniques. The model is based on Multi-Featured Attention Module and Grid-Augmented Module and outperforms the original Transformer model on all evaluation metrics. Specifically, with a beam size of 7, the model achieves a BLEU-4 score of 0.409 and a CIDEr score of 1.008.\",\"PeriodicalId\":276778,\"journal\":{\"name\":\"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)\",\"volume\":\"9 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AINIT59027.2023.10212804\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AINIT59027.2023.10212804","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

本文利用计算机视觉和自然语言处理技术，提出了一种基于transformer的图像字幕模型。该模型基于多特征注意力模块和网格增强模块，在所有评价指标上都优于原Transformer模型。其中，当光束尺寸为7时，该模型的BLEU-4得分为0.409,CIDEr得分为1.008。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Balanced Overall and Local: Improving Image Captioning with Enhanced Transformer Model

This article proposes a Transformer-based image captioning model using computer vision and natural language processing techniques. The model is based on Multi-Featured Attention Module and Grid-Augmented Module and outperforms the original Transformer model on all evaluation metrics. Specifically, with a beam size of 7, the model achieves a BLEU-4 score of 0.409 and a CIDEr score of 1.008.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)

自引率

0.00%

发文量