Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights
Paper
• 2407.11449 • Published
Model Source
Model Checkpoints for ECCV 2024 Paper: Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights Unzip the model weights and place their path in the config files accordingly for inference.
- Repository: https://github.com/ShunqiM/Ctrl-CIC
- Paper: https://arxiv.org/abs/2407.11449
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support