Connecting Vision and Language with Localized Narratives

We propose Localized Narratives, an efficient way to collect image captions with dense visual grounding. We ask annotators to describe an image with their voice while simultaneously hovering their mouse over the region they are describing. Since the voice and the mouse pointer are synchronized, we can localize every single word in the description. This dense visual grounding takes the form of a mouse trace segment per word and is unique to our data. We annotate 628k images with Localized Narratives: the whole COCO dataset and 504k images of the Open Images dataset, which we make publicly available. We provide an extensive analysis of these annotations and demonstrate their utility on two applications which benefit from our mouse trace: controlled image captioning and image generation.