Existing video recognition algorithms always conduct different training
...
Anomaly detection in videos is a significant yet challenging problem.
Pr...
The state of neural network pruning has been noticed to be unclear and e...
Existing action recognition methods typically sample a few frames to
rep...
A deeper network structure generally handles more complicated non-linear...
In recent years, change point detection for high dimensional data has be...
Fully exploiting the learning capacity of neural networks requires
overp...
The fast transmission rate of COVID-19 worldwide has made this virus the...
Action prediction aims to infer the forthcoming human action with
partia...
Anomaly detection is a fundamental yet challenging problem in machine
le...
Sign language is commonly used by deaf or mute people to communicate but...
Vector Auto-Regressive (VAR) models capture lead-lag temporal dynamics o...
Several recent works [40, 24] observed an interesting phenomenon in neur...
Sign language is a visual language that is used by deaf or speech impair...
Advances in face rotation, along with other face-based generative tasks,...
Multi-view action recognition (MVAR) leverages complementary temporal
in...
Multi-view time series classification aims to fuse the distinctive tempo...
In representation learning and non-linear dimension reduction, there is ...
In this work we propose a framework for improving the performance of any...
We propose a new framework for image classification with deep neural
net...