Search Results for author:
Found 1 papers, 0 papers with code
The ImageNet Shuffle: Reorganized Pre-training for Video Event Detection
To deal with the problems of over-specific classes and classes with few images, we introduce a bottom-up and top-down approach for reorganization of the ImageNet hierarchy based on all its 21, 814 classes and more than 14 million images.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
