Using graph neural networks (GNNs) to approximate specific functions suc...
Fusing the camera and LiDAR information has become a de-facto standard f...
Persistent homology is a widely used theory in topological data analysis...
Inductive relation prediction is an important learning task for knowledg...
Consistent performance gains through exploring more effective network
st...
Malicious application of deepfakes (i.e., technologies can generate targ...
Large-scale pre-trained models like BERT, have obtained a great success ...
Math expressions are important parts of scientific and educational docum...
Although the content in scientific publications is increasingly challeng...
Nowadays, general object detectors like YOLO and Faster R-CNN as well as...
Recently, neural architecture search (NAS) has been exploited to design
...
Link prediction is an important learning task for graph-structured data....
Despite the recent advances in optical character recognition (OCR),
math...
Existing CNN-based methods for pixel labeling heavily depend on multi-sc...
To efficiently extract spatiotemporal features of video for action
recog...
Feature pyramids are widely exploited in many detectors to solve the sca...
Mathematical equations are an important part of dissemination and
commun...
In existing CNN based detectors, the backbone network is a very importan...
Zero-shot and few-shot learning aim to improve generalization to unseen
...
Graph convolutional neural networks (GCNNs) have been attracting increas...
Although the scientific digital library is growing at a rapid pace,
scho...
Feature pyramids are widely exploited by both the state-of-the-art one-s...
Digital signs(such as barcode or QR code) are widely used in our daily l...