Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
This work addresses the problem of generating accurate captions and answering complex visual questions for AI systems, representing an incremental improvement by enhancing existing methods with explicit concepts and knowledge integration.
The paper tackles vision-to-language tasks by incorporating high-level semantic concepts and external knowledge into CNN-RNN models, achieving state-of-the-art results in image captioning and visual question answering on multiple benchmark datasets.
Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism can be used to incorporate external knowledge, which is critically important for answering high level visual questions. Specifically, we design a visual question answering model that combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. It particularly allows questions to be asked about the contents of an image, even when the image itself does not contain a complete answer. Our final model achieves the best reported results on both image captioning and visual question answering on several benchmark datasets.