Stable Diffusion (SD) customization approaches enable users to personali...
Dynamic neural network is an emerging research topic in deep learning. W...
Knowledge distillation is a popular technique for transferring the knowl...
Current outdoor LiDAR-based 3D object detection methods mainly adopt the...
Compared to query-based black-box attacks, transfer-based black-box atta...
Unsupervised object discovery (UOD) has recently shown encouraging progr...
Differentiable architecture search (DARTS) has significantly promoted th...
There are two critical sensors for 3D perception in autonomous driving, ...
Fusing the camera and LiDAR information has become a de-facto standard f...
Scene text recognition (STR) is a challenging problem due to the imperfe...
The development of scene text recognition (STR) in the era of deep learn...
For artificial learning systems, continual learning over time from a str...
Consistent performance gains through exploring more effective network
st...
Malicious application of deepfakes (i.e., technologies can generate targ...
Nowadays, general object detectors like YOLO and Faster R-CNN as well as...
Recently, neural architecture search (NAS) has been exploited to design
...
Lossy compression brings artifacts into the compressed image and degrade...
Data augmentation (DA) techniques aim to increase data variability, and ...
To efficiently extract spatiotemporal features of video for action
recog...
Feature pyramids are widely exploited in many detectors to solve the sca...
In existing CNN based detectors, the backbone network is a very importan...
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...
The ability to detect small objects and the speed of the object detector...