# Face2Text: Collecting an Annotated Image Description Corpus for the Generation of Rich Face Descriptions

## TL;DR

This paper introduces Face2Text, a new face description corpus collected via crowdsourcing, highlighting the diversity of attributes in face descriptions and the challenges they pose for image-to-text generation.

## Contribution

It presents the first annotated corpus of face descriptions and analyzes the variation and complexity of attributes used in describing faces.

## Key findings

- Descriptions include physical, emotional, and inferential attributes.
- Face descriptions are highly diverse and complex.
- Challenges for current image-to-text models are identified.

## Abstract

The past few years have witnessed renewed interest in NLP tasks at the interface between vision and language. One intensively-studied problem is that of automatically generating text from images. In this paper, we extend this problem to the more specific domain of face description. Unlike scene descriptions, face descriptions are more fine-grained and rely on attributes extracted from the image, rather than objects and relations. Given that no data exists for this task, we present an ongoing crowdsourcing study to collect a corpus of descriptions of face images taken `in the wild'. To gain a better understanding of the variation we find in face description and the possible issues that this may raise, we also conducted an annotation study on a subset of the corpus. Primarily, we found descriptions to refer to a mixture of attributes, not only physical, but also emotional and inferential, which is bound to create further challenges for current image-to-text methods.