You're currently viewing an old version of this dataset. To see the current version, click here.

CLIP-DIFFUSION-LM: APPLY DIFFUSION MODEL ON IMAGE CAPTIONING

Image captioning task has been extensively researched by previous work. However, limited experiments focus on generating captions based on non-autoregressive text decoder. Inspired by the recent success of the denoising diffusion model on image synthesis tasks, we apply denoising diffusion probabilistic models to text generation in image captioning tasks.

Data and Resources

Cite this as

Shitong Xu, Imperial College London (2024). Dataset: CLIP-DIFFUSION-LM: APPLY DIFFUSION MODEL ON IMAGE CAPTIONING. https://doi.org/10.57702/roc00gql

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2210.04559
Author Shitong Xu
More Authors
Imperial College London
Homepage https://github.com/xu-shitong/diffusion-image-captioning