Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources
It addresses the problem of answering image-based questions that require external knowledge, which is incremental as it builds on existing neural network approaches.
The paper tackles visual question answering by combining image content with external knowledge bases to answer complex questions, achieving state-of-the-art results on Toronto COCO-QA and MS COCO-VQA datasets.
We propose a method for visual question answering which 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. This allows more complex questions to be answered using the predominant neural network-based approach than has previously been possible. It particularly allows questions to be asked about the contents of an image, even when the image itself does not contain the whole answer. The method constructs a textual representation of the semantic content of an image, and merges it with textual information sourced from a knowledge base, to develop a deeper understanding of the scene viewed. Priming a recurrent neural network with this combined information, and the submitted question, leads to a very flexible visual question answering approach. We are specifically able to answer questions posed in natural language, that refer to information not contained in the image. We demonstrate the effectiveness of our model on two publicly available datasets, Toronto COCO-QA and MS COCO-VQA and show that it produces the best reported results in both cases.