What value do explicit high level concepts have in vision to language problems?
This addresses the need for better semantic understanding in vision-to-language problems, offering an incremental enhancement to existing CNN-RNN approaches.
The paper tackled the problem of incorporating high-level semantic concepts into vision-to-language tasks, showing that their method achieves significant improvements in state-of-the-art performance for image captioning and visual question answering, with external semantic information further boosting results.
Much of the recent progress in Vision-to-Language (V2L) 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. We propose here a method of incorporating high-level concepts into the very successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art performance in both image captioning and visual question answering. We also show that the same mechanism can be used to introduce external semantic information and that doing so further improves performance. In doing so we provide an analysis of the value of high level semantic information in V2L problems.