Weakly supervised object localization (WSOL) strives to learn to localiz...
Multi-Object Tracking (MOT) is a crucial computer vision task that aims ...
Deep learning has proved to be very effective in video action recognitio...
Watermarking serves as a widely adopted approach to safeguard media
copy...
Weakly supervised semantic segmentation (WSSS), which aims to mine the o...
Humans tend to mine objects by learning from a group of images or severa...
Real-world visual recognition problems often exhibit long-tailed
distrib...
With the development of Generative Adversarial Network, image-based virt...
Data augmentation is vital for deep learning neural networks. By providi...
Deep learning has brought great progress for the sequential recommendati...
Batch Normalization (BN) has been a standard component in designing deep...
Scene Graph, as a vital tool to bridge the gap between language domain a...
Generative adversarial networks (GANs) have shown remarkable success in
...
The outbreak of novel coronavirus disease 2019 (COVID-19) has already
in...
Portfolio Selection is an important real-world financial task and has
at...
Online Active Learning (OAL) aims to manage unlabeled datastream by
sele...
Deep learning based medical image diagnosis has shown great potential in...
Learning structural information is critical for producing an ideal resul...
Generating images via the generative adversarial network (GAN) has attra...
Channel pruning is one of the predominant approaches for deep model
comp...
Generative adversarial networks (GANs) aim to generate realistic data fr...
The depth is one of the key factors behind the great success of convolut...