… However, most of the existing models depend heavily on paired image-sentence … an image
captioning model in an unsupervised manner. Instead of relying on manually labeled image-…

… In this paper, we address image captioning by generating language descriptions of scenes
without learning from annotated pairs of images and their captions. The core component of …

… dataset of interests, practitioner needs to annotate the caption for each image in the training
… collected image dataset. In this paper, we explore the task of unsupervised image captioning …

… We test all the existing unsupervised image captioning datasets, including (1) MSCOCO
images [Lin et al., 2014] paired with Shutterstock captions [Feng et al., 2019]; and (2) Flickr30k …

… Considering the long training period of the pre-trained model used by the existing unsupervised
image captioning methods, we propose a simpler and more effective pre-trained model. …

… In Section 5, the objectives of our unsupervised image captioning model are introduced. …
The framework of our unsupervised image captioning model. RMCNet encodes an input image …

… 2) Unsupervised image captioning: We have used the concept of machine translation using
unsupervised technique for image captioning using unsupervised deep learning algorithm. …

… UIC model significantly and consistently, which demonstrates that our TSGAN can improve
the unsupervised image captioning model by a novel method different from SeqGAN [20]. …

… Contrary to these approaches, we focus on employing unsupervised image captioning and
… -captions. Another variation of unpaired image captioning is the generation of captions in one …

… Image Captioning model by projecting the image and caption into the same space to estimate
their similarity. The image … on ImageNet, and the captions are embedded using InferSent [7…