8 datasets found

Face transformer for recognition.

The dataset used for Smart Reply and Ambient Clinical Intelligence tasks

The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis. The data provided by the organizers of the shared task are extracted...

Multichannel speech enhancement model based on transformer architecture and subgroup processing

CogVideo is a large-scale pretrained transformer for text-to-video generation. It is trained on a dataset of 5.4 million captioned videos with a spatial resolution of 160×160.

The proposed YOLO-Former method seamlessly integrates the ideas of transformer and YOLOv4 to create a highly accurate and efficient object detection system.

Action segmentation dataset for supervised action segmentation

Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain.