2 papers
cs.CV2026
StoryMovie: A Dataset for Semantic Alignment of Visual Stories with Movie Scripts and Subtitles
Daniel Oliveira, David Martins de Matos
Visual storytelling models that correctly ground entities in images may still hallucinate semantic relationships, generating incorrect dialogue attribution, character interactions,…
cs.CV2025
GroundCap: A Visually Grounded Image Captioning Dataset
Daniel A. P. Oliveira, Lourenço Teodoro, David Martins de Matos
Current image captioning systems lack the ability to link descriptive text to specific visual elements, making their outputs difficult to verify. While recent approaches offer some…