期刊: PATTERN RECOGNITION, 2021; 116 ()
Heterogeneous information networks usually contain different kinds of nodes and distinguishing types of relations, which can preserve more information......
期刊: PATTERN RECOGNITION, 2021; 116 ()
Prototype-based few-shot learning methods are promising in that they are simple yet effective to handle any-shot problems, and many prototype associat......
期刊: PATTERN RECOGNITION, 2021; 117 ()
Weakly-supervised semantic segmentation, as a promising solution to alleviate the burden of collecting per-pixel annotations, aims to train a segmenta......
期刊: PATTERN RECOGNITION, 2021; 118 ()
Image dehazing is very important for many computer vision tasks. However, typical CNN-based methods learn a direct mapping from a hazy image to a clea......
期刊: PATTERN RECOGNITION, 2021; 119 ()
Traditional pattern recognition problems are usually accomplished through two successive stages of rep-resentation and classification, the generalizat......
期刊: PATTERN RECOGNITION, 2021; 120 ()
Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-leve......
期刊: PATTERN RECOGNITION, 2021; 120 ()
Using medical images for disease identification is an important application in the medical field. Graph Convolutional Network (GCN) is proposed to mod......
期刊: PATTERN RECOGNITION, 2021; 115 ()
Recently, a series of cascaded pose regression based facial landmark localization methods under occlusion have been proposed. However, partial occlusi......
期刊: PATTERN RECOGNITION, 2021; 117 ()
The problem of inhomogeneous cluster densities has been a long-standing issue for distance-based and density-based algorithms in clustering and anomal......
期刊: PATTERN RECOGNITION, 2021; 118 ()
In a previous study, we have explored how to decompose the global entropy of a network into edge components using a graph-spectral decomposition techn......
期刊: PATTERN RECOGNITION, 2021; 120 ()
Accurate segmentation of corneal layers depicted on optical coherence tomography (OCT) images is very helpful for quantitatively assessing and diagnos......
期刊: PATTERN RECOGNITION, 2021; 120 ()
How to identify the most influential nodes in a network for the maximization of influence spread is a great challenge. Known methods like k-shell deco......
期刊: PATTERN RECOGNITION, 2021; 120 ()
Video based visual question answering (V-VQA) remains challenging at the intersection of vision and language. In this paper, we propose a novel archit......
期刊: PATTERN RECOGNITION, 2021; 115 ()
Multi-view data may lose some instances in real applications. Most existing methods for clustering such incomplete multi-view data still have at least......
期刊: PATTERN RECOGNITION, 2021; 117 ()
Object detection is an important field in computer vision. Nevertheless, a research area that has so far not received much attention is the study into......