7 datasets found

Chinese–Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information

Unsupervised domain generalization (UDG) aims to learn generalizable models with unlabeled data and analyze the effects of pre-training on DG.

This paper proposes the Davis 2017 validation set for video object segmentation.

The proposed approach is tested on English-German, English-French and Chinese-to-English translation tasks.

MultiShapeNet is a 3D dataset featuring scenes populated by 2-4 objects from the ShapeNetV2 dataset.

CLEVR-3D is a 3D version of the CLEVR dataset, featuring multiple viewpoints, camera positions, and depth information.

The MNIST dataset (Lecun et al., 1998), which consists of 60,000 gray-scale images of handwritten digits. Each image has an accompanying label in {0, 1,..., 9}, and is stored as...