Convolutional neural networks (CNNs) have been applied to visual tasks since the late
1980s. However, despite a few scattered applications, they were dormant until the mid …

In recent years, deep neural networks (DNNs) have received increased attention, have been
applied to different applications, and achieved dramatic accuracy improvements in many …

We propose a novel neural representation for videos (NeRV) which encodes videos in
neural networks. Unlike conventional representations that treat videos as frame sequences …

In recent years, deep neural networks have been successful in both industry and academia,
especially for computer vision tasks. The great success of deep learning is mainly due to its …

Pre-trained language models such as BERT have proven to be highly effective for natural
language processing (NLP) tasks. However, the high demand for computing resources in …

Deep neural networks (DNNs) have recently achieved great success in many visual
recognition tasks. However, existing deep neural network models are computationally …

In computer vision, convolutional networks (CNNs) often adopt pooling to enlarge receptive
field which has the advantage of low computational complexity. However, pooling can cause …

The input to a machine learning model is a one-dimensional feature vector. However, in
recent learning models, such as convolutional and recurrent neural networks, two-and three …

In this paper, we propose a novel model compression approach to effectively compress
BERT by progressive module replacing. Our approach first divides the original BERT into …

Unsupervised deep hash functions have not shown satisfactory improvements against the
shallow alternatives, and usually, require supervised pretraining to avoid getting stuck in …