Vaibhav Pandit, Rishabh Gulati, Chaitanya Singla, Sandeep Kr. Singh
{"title":"DeepCap:一种用于描述黑白图像的深度学习模型","authors":"Vaibhav Pandit, Rishabh Gulati, Chaitanya Singla, Sandeep Kr. Singh","doi":"10.1109/Confluence47617.2020.9058164","DOIUrl":null,"url":null,"abstract":"Captioning of colored images has been around for quite some time now, it uses object detection and the spatial relation between the objects to generate captions. There have been numerous approaches to caption colorized images in the past, but there have been a very few. In this paper we present an approach to caption Black and white images without any attempt of colorization. We have used transfer learning to implement Inception V3, a CNN model developed by Google and a runner up in the ImageNet image classification challenge, to generate captions from Black and white images achieving an accuracy of 45.77% on the validation set.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"DeepCap: A Deep Learning Model to Caption Black and White Images\",\"authors\":\"Vaibhav Pandit, Rishabh Gulati, Chaitanya Singla, Sandeep Kr. Singh\",\"doi\":\"10.1109/Confluence47617.2020.9058164\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Captioning of colored images has been around for quite some time now, it uses object detection and the spatial relation between the objects to generate captions. There have been numerous approaches to caption colorized images in the past, but there have been a very few. In this paper we present an approach to caption Black and white images without any attempt of colorization. We have used transfer learning to implement Inception V3, a CNN model developed by Google and a runner up in the ImageNet image classification challenge, to generate captions from Black and white images achieving an accuracy of 45.77% on the validation set.\",\"PeriodicalId\":180005,\"journal\":{\"name\":\"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/Confluence47617.2020.9058164\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/Confluence47617.2020.9058164","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
DeepCap: A Deep Learning Model to Caption Black and White Images
Captioning of colored images has been around for quite some time now, it uses object detection and the spatial relation between the objects to generate captions. There have been numerous approaches to caption colorized images in the past, but there have been a very few. In this paper we present an approach to caption Black and white images without any attempt of colorization. We have used transfer learning to implement Inception V3, a CNN model developed by Google and a runner up in the ImageNet image classification challenge, to generate captions from Black and white images achieving an accuracy of 45.77% on the validation set.