Extreme edge platforms, such as in-vehicle smart devices, require effici...
Recent studies have shown that dense retrieval models, lacking dedicated...
Visual relation extraction (VRE) aims to extract relations between entit...
Prompt tuning is a parameter-efficient method, which freezes all PLM
par...
As an application of Natural Language Processing (NLP) techniques, finan...
Deep learning-based point cloud processing plays an important role in va...
Ubiquitous internet access is reshaping the way we live, but it is
accom...
In a customer service system, dialogue summarization can boost service
e...
Automatic chat summarization can help people quickly grasp important
inf...
Designing hardware accelerators for deep neural networks (DNNs) has been...
Valentine Day February 14, is the day of love. The days ahead of Valenti...
With the increasing size of Deep Neural Network (DNN) models, the high m...
Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promis...
The Connectionist Temporal Classification (CTC) has achieved great succe...
Deep neural networks (DNNs) have been proven to have many redundancies.
...
The Alternating Direction Method of Multipliers (ADMM) decoding of Low
D...
Deep convolutional neural network (DCNN) has achieved remarkable perform...