LiDAR-based 3D detection has made great progress in recent years. Howeve...
Effective feature fusion of multispectral images plays a crucial role in...
Semantic segmentation of drone images is critical to many aerial vision ...
In this paper, we propose an embarrassingly simple yet highly effective
...
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels h...
In recent years, deep convolutional neural networks (CNN) have significa...
Time series forecasting is crucial for many fields, such as disaster war...
Robustness and discrimination power are two fundamental requirements in
...
We present a Siamese-like Dual-branch network based on solely Transforme...
Video based fall detection accuracy has been largely improved due to the...
LiDAR-based 3D object detection pushes forward an immense influence on
a...
A big, diverse and balanced training data is the key to the success of d...
Existing template-based trackers usually localize the target in each fra...
Neural Architecture Search (NAS) technologies have been successfully
per...
Eyeglasses removal is challenging in removing different kinds of eyeglas...
Conventional multi-view re-ranking methods usually perform asymmetrical
...
In recent years, visual question answering (VQA) has become topical. The...
In recent years, visual question answering (VQA) has become topical as a...
Studies show that refining real-world categories into semantic subcatego...
The "CNN-RNN" design pattern is increasingly widely applied in a variety...