A survey on automatic image caption generation

Bai, Song; An, Shan

doi:10.1016/j.neucom.2018.05.080

Cited by 196 publications

(118 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Given the scientific and practical importance of the natural language based description of images, it has been a very dynamic research endeavour with tools and techniques of both traditional machine learning and deep machine learning have been brought to bear on achieving expected performance [13][14][15]. However, restricted scope of the vocabularies for describing visual contents limits the varieties of narratives about a visual space, and the template based image description restricts complex and varied sematic interpretation, though descriptor models can produce grammatically correct texts.…”

Section: Figure 1 Extraction Of a Simple Natural Language Descriptiomentioning

confidence: 99%

Natural language description of images using hybrid recurrent neural network

Jishan¹,

Mahmud²,

Azad³

2019

IJECE

View full text Add to dashboard Cite

We presented a learning model that generated natural language description of images. The model utilized the connections between natural language and visual data by produced text line based contents from a given image. Our Hybrid Recurrent Neural Network model is based on the intricacies of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bi-directional Recurrent Neural Network (BRNN) models. We conducted experiments on three benchmark datasets, e.g., Flickr8K, Flickr30K, and MS COCO. Our hybrid model utilized LSTM model to encode text line or sentences independent of the object location and BRNN for word representation, this reduced the computational complexities without compromising the accuracy of the descriptor. The model produced better accuracy in retrieving natural language based description on the dataset.

show abstract

Section: Figure 1 Extraction Of a Simple Natural Language Descriptiomentioning

confidence: 99%

Natural language description of images using hybrid recurrent neural network

Jishan¹,

Mahmud²,

Azad³

2019

IJECE

View full text Add to dashboard Cite

show abstract

“…We can only mention the highlighted objects and their attributes but not in fine deeper way. Jonathan Krause"s [6] model solves this problem. The hierarchical recurrent networks help in identifying the image keenly.…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Caption and Emoji of an Image using Deep Learning

2019

IJRTE

View full text Add to dashboard Cite

With the invention of deep learning, there is a good progress in image classification. But automatic generation of captions for images is still a challenging problem and is in the initial stages of artificial intelligence research. Automatic description of images has applications in social networking and will be useful to visually impaired persons. This paper concentrates on designing a user-friendly web application framework which can predict the caption of an image using deep learning techniques. The verbs and objects present in the caption are used for forming the emoji and for predicting the major color of the image

show abstract

“…We can only mention the highlighted objects and their attributes but not in fine deeper way. Jonathan Krause [2] presented a model which overcomes this problem. The hierarchical recurrent networks help in identifying the image keenly.…”

Section: Nivedita Asnath Victy Phamila Ymentioning

confidence: 99%

Image Captioning for Affine Transformed Images using Image Hashing

2019

IJEAT

View full text Add to dashboard Cite

Image captioning is the process of generating a meaningful textual description to the image. The perfect caption for the image not only consists of objects and their attributes, it also concentrates on the actions involved by the objects. There are two main tasks in Image captioning. The first and foremost task is correctly identifying objects present in the given image. Once all the objects are identified along with their attributes, the dense model is trained in order to identify the correct verbs or the actions in which these identified objects are involved. The second part in Image captioning is generating the syntactically correct natural language sentence which connects all the identified objects along with their attributes and actions. In this paper we have generated the captioning for affine transformed images using Flickr 8K dataset.

show abstract

A survey on automatic image caption generation

Cited by 196 publications

References 37 publications

Natural language description of images using hybrid recurrent neural network

Natural language description of images using hybrid recurrent neural network

Prediction of Caption and Emoji of an Image using Deep Learning

Image Captioning for Affine Transformed Images using Image Hashing

Contact Info

Product

Resources

About