m-Just/VisCoT_VStar_Collage download history
m-Just/VisCoT_VStar_Collage is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 312 times (80 in the last 7 days), and 9,156 times in total. It ranks #47,620 among datasets by monthly downloads.
This is part of the training data for vSearcher introduced in "InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search". The data comprise collages made from a subset of images from VisualCoT and the training data of V*. Each entry of this dataset contains a collage (with