Adversarial Image Caption Generator Network

Research output: Contribution to journalArticlepeer-review

Electronic versions

  • Ali Mollaahmadi Dehaqi
    Azad University
  • Vahid Seydi
    Azad University
  • Yeganeh Madadi
    University of Tehran
Image captioning is a task to make an image description, which needs recognizing the important attributes and also their relationships in the image. This task requires to generate semantically and syntactically correct sentences. Most image captioning models are based on RNN and MLE methods, but we propose a novel model based on GAN networks where it generates the caption of the image through the representation of the image by utilizing the generator adversarial network and it does not need any secondary learning algorithm like policy gradient. Due to the complexity of benchmark datasets such as Flickr and Coco, in both volume and complexity, we introduce a new dataset and perform the experiments on it. The experimental results show the effectiveness of our model compared to the state-of-the-art image captioning methods.


  • image captioning, Feature representation, Deep neural network, Generative adversarial network, Novel dataset
Original languageEnglish
Article number182
Number of pages14
Journal SN Computer Science
Issue number3
Early online date31 Mar 2021
Publication statusPublished - May 2021
Externally publishedYes
View graph of relations