Image inpainting for completing complicated semantic environments and di...
Terahertz (THz) tomographic imaging has recently attracted significant
a...
Optical-flow-based and kernel-based approaches have been widely explored...
Recently, great progress has been made in single-image super-resolution
...
Most previous deblurring methods were built with a generic model trained...
Convolutional neural networks (CNNs) have obtained remarkable performanc...
Understanding foggy image sequence in the driving scenes is critical for...
CNNs with strong learning abilities are widely chosen to resolve
super-r...
Images taken in dynamic scenes may contain unwanted motion blur, which
s...
This paper focuses on filter-level network pruning. A novel pruning meth...
Learning-based pre-simulation (i.e., layout-to-fabrication) models have ...
Although considerable progress has been made in semantic scene understan...
We study the problem of efficiently summarizing a short video into sever...
Channel Pruning has been long adopted for compressing CNNs, which
signif...
Terahertz tomographic imaging has recently arisen significant attention ...
Deep convolutional neural networks (CNNs) have been widely applied for
l...
Label noise in training data can significantly degrade a model's
general...
Binary neural networks (BNNs) have attracted broad research interest due...
Image motion blur usually results from moving objects or camera shakes. ...
Descriptive region features extracted by object detection networks have
...
Existing inpainting methods have achieved promising performance in recov...
Recently, falsified images have been found in papers involved in researc...
Binary Neural Network (BNN) shows its predominance in reducing the compl...
Few-shot learning is a challenging problem that has attracted more and m...
Deep convolutional neural networks (CNNs) for image denoising have recen...
Completing a corrupted image with correct structures and reasonable text...
The performance of a convolutional neural network (CNN) based face
recog...
Since IC fabrication is costly and time-consuming, it is highly desirabl...
Deep learning techniques have obtained much attention in image denoising...
Referring Expression Comprehension (REC) is an emerging research spot in...
Image deblurring has achieved exciting progress in recent years. However...
Learning representations with diversified information remains an open
pr...
Group re-identification (G-ReID) is an important yet less-studied task. ...
Rapid development of Internet technologies promotes traditional newspape...
Despite generative adversarial networks (GANs) can hallucinate
photo-rea...
Given a large unlabeled set of images, how to efficiently and effectivel...
Dynamic adaptive streaming over HTTP (DASH) has recently been widely dep...
Recent advent in graph signal processing (GSP) has led to the developmen...