Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
Ashim Dahal, Ankit Ghimire, Saydul Akbar Murad +1
Long-video multimodal question answering requires structured reasoning over visual evidence and dialogue, but Large Vision-Language Models (LVLMs) are constrained by context-window…
cs.CV2025
Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation
Ashim Dahal, Ankit Ghimire, Saydul Akbar Murad +1
Evaluating image captions requires cohesive assessment of both visual semantics and language pragmatics, which is often not entirely captured by most metrics. We introduce Redempti…