Post has shared content
MSCOCO in 5 minutes :)
Are you curious what images are in the MS COCO dataset? See all 80,000 MS COCO training images in 5 minutes! The order of the images is determined by walking through a space in which semantically similar images are close together. Specifically, we use the fc7 features fine-tuned on image captions (From Captions to Visual Concepts and Back, Fang et al., CVPR 2015). Thanks to for sharing his code, and for helping create the video.
Add a comment...
2 plus ones
Wait while more posts are being loaded