leaderonehit/GLaVE-1.2M download history
leaderonehit/GLaVE-1.2M is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 169 times (25 in the last 7 days), and 537 times in total. It ranks #76,874 among datasets by monthly downloads.
GLaVE-1.2M GLaVE-1.2M is the training dataset released with GLaVE-Cap: Global-Local Aligned Video Captioning with Vision Expert Integration. It contains fine-grained video captions, intermediate local annotations, scene-level annotations, and multiple-choice question-answer pairs for