Cross-modal distillation has been widely used to transfer knowledge acro...
Random label noises (or observational noises) widely exist in practical
...
Long-term time-series forecasting (LTTF) has become a pressing demand in...
While deep learning succeeds in a wide range of tasks, it highly depends...
Different from the general visual classification, some classification ta...
Interactive image segmentation aims at segmenting a target region throug...
While fine-tuning pre-trained networks has become a popular way to train...
Pool-based Active Learning (AL) has achieved great success in minimizing...
To understand human behaviors, action recognition based on videos is a c...
With the increasing diversity of ML infrastructures nowadays, distribute...
Active Learning (AL) is a set of techniques for reducing labeling cost b...
Due to privacy concerns of users and law enforcement in data security an...
As the COVID-19 pandemic rampages across the world, the demands of video...
The operation and management of intelligent transportation systems (ITS)...
Principal component analysis (PCA) has been widely used as an effective
...
We find that different Deep Neural Networks (DNNs) trained with the same...
Contrastive learning has been widely applied to graph representation
lea...
While artificial neural networks (ANNs) have been widely adopted in mach...
Existing interpretation algorithms have found that, even deep models mak...
While deep learning succeeds in a wide range of tasks, it highly depends...
Drug discovery often relies on the successful prediction of protein-liga...
In this paper, we develop face.evoLVe – a comprehensive library that
col...
Mobile Sensing Apps have been widely used as a practical approach to col...
Although many techniques have been applied to matrix factorization (MF),...
In modern internet industries, deep learning based recommender systems h...
In recent years, data and computing resources are typically distributed ...
To improve the performance of deep learning, mixup has been proposed to ...
Deep neural networks have been well-known for their superb performance i...
The novel coronavirus disease (COVID-19) has crushed daily routines and ...
Accurately predicting the binding affinity between drugs and proteins is...
Fine-tuning deep neural networks pre-trained on large scale datasets is ...
Transferring knowledge from large source datasets is an effective way to...
Fine-tuning the deep convolution neural network(CNN) using a pre-trained...
Softening labels of training datasets with respect to data representatio...
Arbitrary image style transfer is a challenging task which aims to styli...
Associating sound and its producer in complex audiovisual scene is a
cha...
The key challenge in photorealistic style transfer is that an algorithm
...
Federated machine learning systems have been widely used to facilitate t...
Transfer learning have been frequently used to improve deep neural netwo...
Universal style transfer is an image editing task that renders an input
...
The randomness in Stochastic Gradient Descent (SGD) is considered to pla...
Neural Architecture Search (NAS) has been widely studied for designing
d...
Transfer learning through fine-tuning a pre-trained neural network with ...
We interpret the variational inference of the Stochastic Gradient Descen...
In the past few years, we have envisioned an increasing number of busine...