Showing papers in "Pattern Recognition in 2022"

TL;DR: Wang et al. as mentioned in this paper proposed edge computing based video pre-processing to eliminate the redundant frames, so that they migrate the partial or all the video processing task to the edge, thereby diminishing the computing, storage and network bandwidth requirements of the cloud center, and enhancing the effectiveness of video analyzes.

TL;DR: Zhang et al. as mentioned in this paper proposed a novel approach to estimate both aleatoric and epistemic uncertainties for stereo matching in an end-to-end way, where the uncertainty parameters are predicted for each potential disparity and then averaged via the guidance of matching probability distribution.

TL;DR: Wang et al. as mentioned in this paper proposed edge computing based video pre-processing to eliminate the redundant frames, so that they migrate the partial or all the video processing task to the edge, thereby diminishing the computing, storage and network bandwidth requirements of the cloud center, and enhancing the effectiveness of video analyzes.

TL;DR: In this paper, a neighborhood linear discriminant analysis (nLDA) is proposed, in which the scatter matrices are defined on a neighborhood consisting of reverse nearest neighbors and the neighborhood can be naturally regarded as the smallest subclass.

TL;DR: In this article , a neighborhood linear discriminant analysis (nLDA) is proposed to address multimodality in LDA, in which the scatter matrices are defined on a neighborhood consisting of reverse nearest neighbors.

TL;DR: In this article , a multi-scale visual transformer model, referred as GasHis-Transformer, is proposed for Gastric Histopathological Image Detection (GHID), which enables the automatic global detection of gastric cancer images.

TL;DR: A novel convolution autoencoder architecture that can dissociate the spatio-temporal representation to separately capture the spatial and the temporal information is explored, since abnormal events are usually different from the normality in appearance and/or motion behavior.

TL;DR: In this article, a multi-view deep autoencoder model is proposed to fuse the spectral and spatial features extracted from the hyperspectral image into a joint latent representation space.

TL;DR: In this paper , a multi-view deep autoencoder model is proposed to fuse the spectral and spatial features extracted from the hyperspectral image into a joint latent representation space.

TL;DR: SARS-Net as mentioned in this paper is a CADx system combining graph convolutional networks and Convolutional Neural Networks for detecting abnormalities in a patient's CXR images for presence of severe acute respiratory syndrome coronavirus.

TL;DR: SARS-Net as discussed by the authors is a CADx system combining graph convolutional networks and Convolutional Neural Networks for detecting abnormalities in a patient's CXR images for presence of severe acute respiratory syndrome coronavirus.

TL;DR: A novel encoder-decoder architecture, called contextual ensemble network (CENet), for semantic segmentation, where the contextual cues are aggregated via densely usampling the convolutional features of deep layer to the shallow deconvolutional layers.

TL;DR: Action Transformer (AcT) as discussed by the authors exploits 2D pose representations over small temporal windows, providing a low latency solution for accurate and effective real-time performance, which consistently outperforms more elaborated networks that mix convolutional, recurrent and attentive layers.

TL;DR: In this article , a multi-modality graph neural network (MAGNN) is proposed to learn from these multimodal inputs for financial time series prediction, which provides investors with a profitable as well as interpretable option and enables them to make informed investment decisions.

TL;DR: In this paper, an uncertainty-aware mean teacher is incorporated into the scribble-based segmentation method, encouraging the segmentation predictions to be consistent under different perturbations for an input image.

TL;DR: In this article, a multi-modality graph neural network (MAGNN) is proposed to learn from these multimodal inputs for financial time series prediction, which provides investors with a profitable as well as interpretable option and enables them to make informed investment decisions.

TL;DR: In this paper , an uncertainty-aware mean teacher is incorporated into the scribble-based segmentation method, encouraging the segmentation predictions to be consistent under different perturbations for an input image.

TL;DR: In this article, a polarization fusion network with geometric feature embedding (PFGFE-Net) was proposed to solve the two defects of traditional feature abandonment and insufficient utilization of traditional features.

TL;DR: Zhang et al. as discussed by the authors proposed an effective bidirectional pyramid architecture to enhance internal representations of features to cater to fine-grained image recognition task in the few-shot learning scenario.

TL;DR: An underwater image enhancement method that does not require training on synthetic underwater images and eliminates the dependence on underwater ground-truth images is presented and the experimental results indicate that the proposed method produces visually satisfactory results.

TL;DR: In this paper , a high-order coverage function (HCF) neuron model was proposed to replace the fully-connected (FC) layers, which utilizes weight coefficients and hyper-parameters to mine underlying geometry with arbitrary shapes in an n-dimensional space.

TL;DR: In this article , a polarization fusion network with geometric feature embedding (PFGFE-Net) was proposed to solve the two defects of traditional feature abandonment and insufficient utilization of traditional features.

TL;DR: In this paper , a comprehensive survey of 3D object detection for autonomous driving is presented, encompassing all the main concerns including sensors, datasets, performance metrics and the recent state-of-the-art detection methods, together with their pros and cons.

TL;DR: Wang et al. as discussed by the authors proposed a novel convolution autoencoder architecture that can dissociate the spatio-temporal representation to separately capture the spatial and temporal information, since abnormal events are usually different from the normality in appearance and/or motion behavior.

TL;DR: A comprehensive survey of image augmentation for deep learning using a novel informative taxonomy is presented in this article , where the algorithms are classified into three categories: model-free, model-based, and optimizing policy-based.

TL;DR: Wang et al. as discussed by the authors proposed the Embedding Unmasking Model (EUM) operated on top of existing face recognition models, which enabled the EUM to produce embeddings similar to these of unmasked faces of the same identities.

TL;DR: In this article , a taxonomy of X-ray security imaging algorithms is presented, with a particular focus on object classification, detection, segmentation and anomaly detection tasks, and a performance benchmark is provided based on the current and future trends in deep learning.

TL;DR: In this paper, a taxonomy of X-ray security imaging algorithms is presented, with a particular focus on object classification, detection, segmentation and anomaly detection tasks, and a performance benchmark is provided based on the current and future trends in deep learning.

TL;DR: Wang et al. as mentioned in this paper proposed a high frequency attention-guided Siamese network (HFA-Net), which is composed of two main stages, spatial-wise attention (SA) and high frequency enhancement (HF).

TL;DR: In this paper , a 2D convolutional model was proposed to predict the future trajectories of pedestrians, which achieved state-of-the-art results on the ETH and TrajNet datasets.