SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning
Refines noisy synthetic image-caption datasets through a one-to-many mapping that re-aligns each image with its best-matching captions.
Content tagged with "zero-shot captioning"
Refines noisy synthetic image-caption datasets through a one-to-many mapping that re-aligns each image with its best-matching captions.
Zero-shot image captioning for in-vehicle driver monitoring, generating natural-language descriptions of driver states. Funded by Hyundai NGV (2024).