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

TY - GEN

T1 - Face2Text: Collecting an Annotated Image Description Corpus for the Generation of Rich Face Descriptions

AU - Gatt, Albert

AU - Tanti, Marc

AU - Muscat, Adrian

AU - Paggio, Patrizia

AU - Farrugia, Reuben

AU - Borg, Claudia

AU - Camilleri, Kenneth

AU - Rosner, Mike

AU - van der Plas, Lonneke

PY - 2018

Y1 - 2018

N2 - 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

AB - 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

M3 - Article in proceedings

BT - Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

PB - European Language Resources Association

CY - Miyazaki

ER -