10 datasets found

A novel benchmark for multi-label image classification in medical imaging, combining new classes and domains into a challenging scenario.

The dataset used in the Continual Robot Imitation Learning (CRIL) paper, which consists of pseudo demonstrations of learned tasks and real demonstrations of new tasks.

The Continual World benchmark consists of ten realistic robotic manipulation tasks.

A federated and continual learning framework for classification tasks in a society of devices

The dataset used in the paper is the Split MS-COCO dataset, which is a comprehensive framework for continual image captioning.

The UCF101 dataset contains 13320 videos distributed in 101 action categories. This dataset is different from the above ones in that it contains mostly coarse sports activities...

The Kinetics dataset is a large-scale human action dataset, which consists of 400 action classes where each category has more than 400 videos.

CORe50 is a video benchmark for continual learning, consisting of 164,866 128x128 images of 50 domestic objects belonging to 10 categories.

This dataset is a continual deepfake detection benchmark, which contains images across different domains.

Temporal activity detection has drawn increasing interests in both academic and industry communities due to its vast potential applications in security surveillance, behavior...