IEEE transactions on pattern analysis and machine intelligence
Apr 1, 2022
Objective measures of image quality generally operate by comparing pixels of a "degraded" image to those of the original. Relative to human observers, these measures are overly sensitive to resampling of texture regions (e.g., replacing one patch of ...
IEEE transactions on pattern analysis and machine intelligence
Apr 1, 2022
Despite the success of convolutional neural network (CNN) in conventional closed-set recognition (CSR), it still lacks robustness for dealing with unknowns (those out of known classes) in open environment. To improve the robustness of CNN in open-set...
IEEE transactions on pattern analysis and machine intelligence
Apr 1, 2022
Constructive solid geometry (CSG) is a geometric modeling technique that defines complex shapes by recursively applying boolean operations on primitives such as spheres and cylinders. We present CSGNet, a deep network architecture that takes as input...
IEEE transactions on pattern analysis and machine intelligence
Apr 1, 2022
The generator in generative adversarial networks (GANs) is driven by a discriminator to produce high-quality images through an adversarial game. At the same time, the difficulty of reaching a stable generator has been increased. This paper focuses on...
IEEE transactions on pattern analysis and machine intelligence
Apr 1, 2022
We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply light-weight convolutional filtering across each dimension of the input t...
IEEE transactions on pattern analysis and machine intelligence
Mar 4, 2022
Adversarial attacks on deep neural networks (DNNs) have been found for several years. However, the existing adversarial attacks have high success rates only when the information of the victim DNN is well-known or could be estimated by the structure s...
IEEE transactions on pattern analysis and machine intelligence
Mar 4, 2022
Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the most wide...
IEEE transactions on pattern analysis and machine intelligence
Mar 4, 2022
Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantages of human ingenuity and prior knowledge. Thus it h...
IEEE transactions on pattern analysis and machine intelligence
Mar 4, 2022
Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by...
IEEE transactions on pattern analysis and machine intelligence
Mar 4, 2022
Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention bas...