UIT-ViIC: A Dataset for the First Evaluation on Vietnamese Image Captioning

Image Captioning (IC), the task of automatic generation of image captions, has attracted attentions from researchers in many fields of computer science, being computer vision, natural language processing and machine learning in recent years. This paper contributes to research on Image Captioning task in terms of extending dataset to a different language - Vietnamese. So far, there has been no existed Image Captioning dataset for Vietnamese language, so this is the foremost fundamental step for developing Vietnamese Image Captioning. In this scope, we first built a dataset which contains manually written captions for images from Microsoft COCO dataset relating to sports played with balls, we called this dataset UIT-ViIC (University Of Information Technology - Vietnamese Image Captions). UIT-ViIC consists of 19,250 Vietnamese captions for 3,850 images. Following that, we evaluated our dataset on deep neural network models and did comparisons with English dataset and two Vietnamese datasets built by different methods. UIT-ViIC is published on our lab website (https://​sites.​google.​com/​uit.​edu.​vn/​uit-nlp/​) for research purposes.