Generating image captions in Polish – experimental study
Authors:
- 8 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
The image captioning task focuses on generating sentences describing the content of a given image. Recently, some end-to-end solutions based on complex deep neural networks were proposed. However, most of them are producing captions in English, which is a syntactically relatively simple language. Application of captioning methods to more sophisticated languages, e.g., fusional, may cause problems due to the complex syntax. In the paper, we describe the initial results of applying the generative model to produce sentences in Polish, which is the fusional language. To validate the method, we used two datasets based on the Flickr8k database. The first is automatically translated Flickr8k, and the second one is the AIDe dataset consisting of 1000 pictures. The results were validated using BLEU, CIDEr, and BoW metrics.Keywords
This publication has 16 references indexed in Scilit:
- Image Captioning using Adversarial Networks and Reinforcement Learning2018
- Where to put the image in an image caption generatorNatural Language Engineering, 2018
- Rethinking the Inception Architecture for Computer Vision2016
- Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data2016
- Common Subspace for Model and Similarity: Phrase Learning for Caption Generation from Images2015
- Deep visual-semantic alignments for generating image descriptions2015
- CIDEr: Consensus-based image description evaluation2015
- Efficient image annotation for automatic sentence generation2012
- The Dynamic Representation of ScenesVisual Cognition, 2000
- WordNetCommunications of the ACM, 1995