Teaching AI to Give Better Video Critiques

Teaching AI to Give Better Video Critiques

While Large Vision-Language Models (LVLMs) can be useful aides in interpreting some of the more arcane or challenging submissions in computer vision literature, there's one area where they are hamstrung: determining the merits and subjective quality of any video examples that accompany new papers*. This is a critical aspect of a submission, since scientific papers often aim to generate excitement through compelling text or visuals – or both. But…