Document AI aims to automatically analyze documents by leveraging natura...
End-to-end (E2E) systems have shown comparable performance to hybrid sys...
3D model reconstruction from a single image has achieved great progress ...
The increasing use of Machine Learning (ML) software can lead to unfair ...
User behavior data produced during interaction with massive items in the...
One of the limitations in end-to-end automatic speech recognition framew...
Code-switching (CS) refers to the phenomenon that languages switch withi...
Intermediate layer output (ILO) regularization by means of multitask tra...
Internal Language Model Estimation (ILME) based language model (LM) fusi...
Attention guidance is an approach to addressing dataset bias in deep
lea...
This paper investigates a new online learning problem with doubly-stream...
High-dimensional and sparse (HiDS) matrices are omnipresent in a variety...
A High-dimensional and sparse (HiDS) matrix is frequently encountered in...
Android allows apps to communicate with its system services via system
s...
3D modeling based on point clouds is an efficient way to reconstruct and...
An end-to-end (E2E) speech recognition model implicitly learns a biased
...
Modeling 3D context is essential for high-performance 3D medical image
a...
Normal map is an important and efficient way to represent complex 3D mod...
Recurrent neural transducer (RNN-T) is a promising end-to-end (E2E) mode...
In this work we propose an inference technique, asynchronous revision, t...
Fluorescein angiography can provide a map of retinal vascular structure ...
This paper addresses a fundamental challenge in 3D medical image process...
In this paper we present a new data-driven method for robust skin detect...
Numerous tasks at the core of statistics, learning and vision areas are
...
Blind image deblurring plays a very important role in many vision and
mu...
Operator splitting methods have been successfully used in computational
...
Frame stacking is broadly applied in end-to-end neural network training ...
Recurrent neural networks (RNNs), especially long short-term memory (LST...
As training data rapid growth, large-scale parallel training with multi-...