Maintaining high efficiency and high precision are two fundamental chall...
While massive valuable deep models trained on large-scale data have been...
This paper proposes an expressive singing voice synthesis system by
intr...
Semantic segmentation is important for scene understanding. To address t...
Human face images usually appear with wide range of visual scales. The
e...
Human pose estimation aims to figure out the keypoints of all people in
...
Vascular segmentation extracts blood vessels from images and serves as t...
While the abuse of deepfake technology has caused serious concerns recen...
Unmanned aerial vehicle (UAV) tracking has wide potential applications i...
The development of Internet technology has continuously intensified the
...
As a representative self-supervised method, contrastive learning has ach...
Salient object detection (SOD) in optical remote sensing images (RSIs), ...
Supervised deep learning depends on massive accurately annotated example...
When encountering a dubious diagnostic case, medical instance retrieval ...
With the recent development of deep convolutional neural networks and
la...
Near-infrared to visible (NIR-VIS) face recognition is the most common c...
Knowledge distillation provides an effective way to transfer knowledge v...
Face recognition is one of the most fundamental and long-standing topics...
Deep face recognition has made remarkable advances in the last few years...
Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, pr...
In this paper we are concerned with the asymptotic analysis of nonbinary...
The limited capacity to recognize faces under occlusions is a long-stand...
The current deep learning based visual tracking approaches have been ver...
Fashion compatibility learning is important to many fashion markets such...
The stunning progress in face manipulation methods has made it possible ...
Concept Factorization (CF) and its variants may produce inaccurate
repre...
Deep neural networks (DNNs) are vulnerable to adversarial attack which i...
Cloud detection plays a very important role in the process of remote sen...
This paper proposes an encoder-decoder network to disentangle shape feat...
Face alignment and 3D face reconstruction are traditionally accomplished...
Contour and skeleton are two complementary representations for shape
rec...