Search Results for author:
Found 3 papers, 3 papers with code
TiDAL: Learning Training Dynamics for Active Learning
Active learning (AL) aims to select the most useful data samples from an unlabeled data pool and annotate them to expand the labeled dataset under a limited budget.
Temporal Convolution for Real-time Keyword Spotting on Mobile Devices
In addition, we release the implementation of the proposed and the baseline models including an end-to-end pipeline for training models and evaluating them on mobile devices.
Ranked #14 on
Keyword Spotting
on Google Speech Commands
(Google Speech Commands V2 12 metric)
Towards Real-Time Automatic Portrait Matting on Mobile Devices
We tackle the problem of automatic portrait matting on mobile devices.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
