Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistenc...
Representation learning has been evolving from traditional supervised
tr...
The scene graph is a new data structure describing objects and their pai...
JPEG images can be further compressed to enhance the storage and transmi...
There has been a recent surge of interest in introducing transformers to...
With the development of generative-based self-supervised learning (SSL)
...
Pooling and unpooling are two essential operations in constructing
hiera...
Graph pooling has been increasingly considered for graph neural networks...
It is promising to solve linear inverse problems by unfolding iterative
...
Recent 2D-to-3D human pose estimation works tend to utilize the graph
st...
Spectral graph convolutional networks (SGCNs) have been attracting incre...
Recent advances in self-supervised learning have experienced remarkable
...
Graph convolution networks, like message passing graph convolution netwo...
Collecting annotated data for semantic segmentation is time-consuming an...
Message passing has evolved as an effective tool for designing Graph Neu...
Substantial experiments have validated the success of Batch Normalizatio...
Feature coding has been recently considered to facilitate intelligent vi...
Graph neural networks have attracted wide attentions to enable represent...
Traffic forecasting has emerged as a core component of intelligent
trans...
To accelerate DNNs inference, low-rank approximation has been widely ado...