TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Image Captioning	Localized Narratives	RCNN + trace positions	CIDEr	106.5	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/connecting-vision-and-language-with-localized/image-captioning-on-localized-narratives)](https://paperswithcode.com/sota/image-captioning-on-localized-narratives?p=connecting-vision-and-language-with-localized)`

Connecting Vision and Language with Localized Narratives

ECCV 2020 · Jordi Pont-Tuset, Jasper Uijlings, Soravit Changpinyo, Radu Soricut, Vittorio Ferrari ·

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.