标题:A survey on deep neural network-based image captioning
作者:Liu, Xiaoxiao; Xu, Qingyang; Wang, Ning
作者机构:[Liu, Xiaoxiao; Xu, Qingyang] Shandong Univ, Sch Mech Elect & Informat Engn, Weihai 264209, Peoples R China.; [Wang, Ning] Dalian Maritime Univ, Mar 更多
通讯作者:Xu, Qingyang;Xu, QY;Wang, N
通讯作者地址:[Xu, QY]Shandong Univ, Sch Mech Elect & Informat Engn, Weihai 264209, Peoples R China;[Wang, N]Dalian Maritime Univ, Marine Engn Coll, Dalian 116026, 更多
来源:VISUAL COMPUTER
出版年:2019
卷:35
期:3
页码:445-470
DOI:10.1007/s00371-018-1566-y
关键词:Image captioning; Image understanding; Object detection; Language model;; Attention mechanism; Dense captioning
摘要:Image captioning is a hot topic of image understanding, and it is composed of two natural parts (look and language expression) which correspond to the two most important fields of artificial intelligence (machine vision and natural language processing). With the development of deep neural networks and better labeling database, the image captioning techniques have developed quickly. In this survey, the image captioning approaches and improvements based on deep neural network are introduced, including the characteristics of the specific techniques. The early image captioning approach based on deep neural network is the retrieval-based method. The retrieval method makes use of a searching technique to find an appropriate image description. The template-based method separates the image captioning process into object detection and sentence generation. Recently, end-to-end learning-based image captioning method has been verified effective at image captioning. The end-to-end learning techniques can generate more flexible and fluent sentence. In this survey, the image captioning methods are reviewed in detail. Furthermore, some remaining challenges are discussed.
收录类别:EI;SCOPUS;SCIE
WOS核心被引频次:1
Scopus被引频次:1
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048271998&doi=10.1007%2fs00371-018-1566-y&partnerID=40&md5=a89ace866b7200390659b92bc4f8010f
TOP