Inserting Faces inside Captions: Image Captioning with Attention Guided Merging

arXiv:2405.02305v1 Announce Type: new
Abstract: Image captioning models are widely used to describe recent and archived pictures with the objective of improving their accessibility and retrieval. Yet, these approaches tend to be inefficient and biased at retrieving people's names. In this work we introduce AstroCaptions, a dataset for the image captioning task. This dataset specifically contains thousands of public fig-ures that are complex to identify for a traditional model. We also propose a novel post-processing method to insert identified people's …

abstract accessibility arxiv attention captioning captions cs.ai cs.cl cs.cv dataset eess.iv image improving inside merging people retrieval type work