laicsiifes/swin-distilbertimbau
Image-to-Text
•
Updated
•
56
•
1
A Comparative Evaluation of Transformer-Based Vision Encoder-Decoder Models for Brazilian Portuguese Image Captioning, by LaICSI (IFES).
Note An union of Swin Transformer and DistilBERTimbau fine-tuned in Flickr30K Portuguese
Note An union of Swin Transformer and GPorTuguese-2 fine-tuned in Flickr30K Portuguese
Note Flickr30K Portuguese Translation with Google Translator API