FashionFAE adds two pre-training tasks, attribute text prediction and text-conditioned image patch reconstruction, and reports state-of-the-art results on FashionGen retrieval and recognition.
Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-training
FashionFAE adds two pre-training tasks, attribute text prediction and text-conditioned image patch reconstruction, and reports state-of-the-art results on FashionGen retrieval and recognition.