3 citations · 12 across the 14 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CV2024★ 1 cited
Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations
Jaisidh Singh, Ishaan Shrivastava, Mayank Vatsa +2
Existing vision-language models (VLMs) treat text descriptions as a unit, confusing individual concepts in a prompt and impairing visual semantic matching and reasoning. An importa…
cs.CV2024★ 2 cited
Exploring Saliency Bias in Manipulation Detection
Joshua Krinsky, Alan Bettis, Qiuyu Tang +2
The social media-fuelled explosion of fake news and misinformation supported by tampered images has led to growth in the development of models and datasets for image manipulation d…