Connecting Vision and Language with Localized Narratives
This work addresses the challenge of creating dense, synchronized multimodal annotations for vision-language tasks, providing a new dataset for researchers in computer vision and natural language processing.
The authors tackled the problem of connecting vision and language by introducing Localized Narratives, a multimodal annotation method where annotators describe images with voice while hovering a mouse over described regions, enabling dense visual grounding of words. They annotated 849k images from datasets like COCO and Open Images, showing the annotations are diverse, accurate, and efficient, and demonstrated utility in controlled image captioning.
We propose Localized Narratives, a new form of multimodal image annotations connecting vision and language. 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 annotated 849k images with Localized Narratives: the whole COCO, Flickr30k, and ADE20K datasets, and 671k images of Open Images, all of which we make publicly available. We provide an extensive analysis of these annotations showing they are diverse, accurate, and efficient to produce. We also demonstrate their utility on the application of controlled image captioning.