Open AccessImage captioning Bot
Author(s) -
Mukund Upadhyay and Prof. Shallu Bashambu
Publication year - 2020
Publication title -
international journal of modern trends in science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-3778
DOI - 10.46501/ijmtst061265
Subject(s) - closed captioning , computer science , semantics (computer science) , artificial intelligence , image (mathematics) , benchmark (surveying) , visualization , process (computing) , object (grammar) , natural language processing , artificial neural network , convolutional neural network , natural language , computer vision , programming language , geodesy , geography
Image captioning means automatically generating a caption for an image with the development of deeplearning, the combination of computer vision and natural language process has caught great attention in thelast few years. Image captioning is a representative of this filed, which makes the computer learn to use oneor more sentences to understand the visual content of an image. The meaningful description generationprocess of highlevel image semantics requires not only the recognition of the object and the scene, but theability of analyzing the state, the attributes and the relationship among these objects. Neural network basedmethods are further divided into subcategories based on the specific framework they use. Each subcategoryof neural network based methods are discussed in detail. After that, state of the art methods are comparedon benchmark datasets. Following that, discussions on future research directions are presented.