qq123aa456

CapDec

CapDec: SOTA Zero Shot Image Captioning Using CLIP and GPT2, EMNLP 2022 (findings)

Remote-sensing-image-captioning-with-transformer-and-multilabel-classification

HMT

The Hierarchical Multiscale Transformer for image caption

CLIP-Caption-Reward

PyTorch code for "Fine-grained Image Captioning with CLIP Reward" (Findings of NAACL 2022)

s-clip

S-CLIP: Semi-supervised Vision-Language Pre-training using Few Specialist Captions

unsupervised_captioning

Code for Unsupervised Image Captioning

qq123aa456/CLIP-Caption-Reward

PyTorch code for "Fine-grained Image Captioning with CLIP Reward" (Findings of NAACL 2022)

qq123aa456/s-clip

S-CLIP: Semi-supervised Vision-Language Pre-training using Few Specialist Captions

qq123aa456/unsupervised_captioning

Code for Unsupervised Image Captioning