5 datasets found

The WSJ corpus is a large vocabulary continuous speech recognition dataset. It contains 36416 sequences, representing around 80 hours of speech.

LVIS: A dataset for large vocabulary instance segmentation.

V3Det is a vast vocabulary visual detection dataset, containing extremely large categories, which consist of 13,029 categories on real-world images.

The dataset used for large-vocabulary semantic segmentation, including ADE20K, Cityscapes, and COCO-Stuff.

Instance segmentation (IS) is an important computer vision task, aiming at simultaneously predicting the class label and the binary mask for each instance of interest in an image.