Face forgery videos have caused severe social public concern, and variou...
Learning from crowds describes that the annotations of training data are...
A number of deep models trained on high-quality and valuable images have...
While massive valuable deep models trained on large-scale data have been...
While the abuse of deepfake technology has caused serious concerns recen...
The development of Internet technology has continuously intensified the
...
Overfitting widely exists in adversarial robust training of deep network...
Supervised deep learning depends on massive accurately annotated example...
Deep networks have strong capacities of embedding data into latent
repre...
In this work, we contribute a new million-scale Unmanned Aerial Vehicle ...
Why should we trust the detections of deep neural networks for manipulat...
Knowledge distillation provides an effective way to transfer knowledge v...
A key for person re-identification is achieving consistent local details...
Accurate temporal action proposals play an important role in detecting
a...
A collection of approaches based on graph convolutional networks have pr...
Image aesthetic quality assessment has been a relatively hot topic durin...
The performance of video saliency estimation techniques has achieved
sig...
Large convolutional neural network models have recently demonstrated
imp...
Typically, the deployment of face recognition models in the wild needs t...
In the coming Virtual/Augmented Reality (VR/AR) era, 3D contents will be...
Aesthetic quality prediction is a challenging task in the computer visio...
Image relighting is to change the illumination of an image to a target
i...
Recently, cloud storage and processing have been widely adopted. Mobile ...
A cloud server spent a lot of time, energy and money to train a Viola-Jo...
In this paper we investigate the aesthetic image classification problem,...