Search Results for author:
Found 2 papers, 1 papers with code
ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation
Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild.
Mitigating Open-Vocabulary Caption Hallucinations
To this end, we propose a framework for addressing hallucinations in image captioning in the open-vocabulary setting.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
