-
Multimodal Fusion for Indoor Sound Source Localization Pattern Recogn. (IF 7.196) Pub Date : 2021-02-23 Jinhui Chen; Ryoichi Takashima; Xingchen Guo; Zhihong Zhang; Xuexin Xu; Tetsuya Takiguchi; Edwin R. Hancock
To identify the localization of indoor sound source, especially when attempted using only a single microphone, it is a challenging problem to machine learning. To address these issues, this paper presents a distinct novel solution based on fusing visual and acoustic models. Therefore, we propose two novel approaches. First, to estimate orientation of vocal object in a stable manner, we employ the visual
-
A new approach for optimal offline time-series segmentation with error bound guarantee Pattern Recogn. (IF 7.196) Pub Date : 2021-02-23 Ángel Carmona-Poyato; Nicolás Luis Fernández-Garcia; Francisco José Madrid-Cuevas; Antonio Manuel Durán-Rosal
Piecewise Linear Approximation is one of the most commonly used strategies to represent time series effectively and approximately. This approximation divides the time series into non-overlapping segments and approximates each segment with a straight line. Many suboptimal methods were proposed for this purpose. This paper proposes a new optimal approach, called OSFS, based on feasible space (FS) [1]
-
Complex Common Spatial Patterns on Time-Frequency Decomposed EEG for Brain-Computer Interface Pattern Recogn. (IF 7.196) Pub Date : 2021-02-23 Vasilisa Mishuhina; Xudong Jiang
Motor imagery brain-computer interface (MI-BCI) has many promising applications but there are problems such as poor classification accuracy and robustness which need to be addressed. We propose a novel approach called time-frequency common spatial patterns (TFCSP) to enhance the robustness and accuracy of the electroencephalogram (EEG) signal classification. The proposed approach decomposes the EEG
-
Vicinal and categorical domain adaptation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-23 Hui Tang; Kui Jia
Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing the labeled source domain. Inspiring results have been acquired by learning domain-invariant deep features via domain-adversarial training. However, its parallel design of task and domain classifiers limits the ability to achieve a finer category-level domain alignment. To
-
Multivariate time series clustering based on complex network Pattern Recogn. (IF 7.196) Pub Date : 2021-02-23 Hailin Li; Zechen Liu
Recent years have seen an increase in research on time series data mining (especially time-series clustering) owing to the widespread existence of time series in various fields. Techniques such as clustering can extract valuable information and potential patterns from time-series data. In this regard, the clustering analysis of multivariate time series is challenging because of the high dimensionality
-
Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning Pattern Recogn. (IF 7.196) Pub Date : 2021-02-22 Seul-Ki Yeom; Philipp Seegerer; Sebastian Lapuschkin; Alexander Binder; Simon Wiedemann; Klaus-Robert Müller; Wojciech Samek
The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the weights of various layers while at the same time aiming to not sacrifice performance. In this paper, we propose a novel criterion for CNN pruning inspired by neural
-
Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing Pattern Recogn. (IF 7.196) Pub Date : 2021-02-12 Yunpei Jia; Jie Zhang; Shiguang Shan; Xilin Chen
Due to the environmental differences, many face anti-spoofing methods fail to generalize to unseen scenarios. In light of this, we propose a unified unsupervised and semi-supervised domain adaptation network (USDAN) for cross-scenario face anti-spoofing, aiming at minimizing the distribution discrepancy between the source and the target domains. Specifically, two modules, i.e., marginal distribution
-
Mean-shift outlier detection and filtering Pattern Recogn. (IF 7.196) Pub Date : 2021-02-08 Jiawei Yang; Susanto Rahardja; Pasi Fränti
Traditional outlier detection methods create a model for data and then label as outliers for objects that deviate significantly from this model. However, when dat has many outliers, outliers also pollute the model. The model then becomes unreliable, thus rendering most outlier detectors to become ineffective. To solve this problem, we propose a mean-shift outlier detector. This detector employs a mean-shift
-
Weakly-supervised semantic segmentation with saliency and incremental supervision updating Pattern Recogn. (IF 7.196) Pub Date : 2021-02-05 Wenfeng Luo; Meng Yang; Weishi Zheng
Weakly-supervised semantic segmentation aims at tackling the dense labeling task using weak supervision so as to reduce human annotation efforts. For weakly-supervised semantic segmentation using only image-level annotation, we propose a novel model of Learning with Saliency and Incremental Supervision Updating (LSISU), in which both the guidances of saliency prior and class information are jointly
-
Few-shot prototype alignment regularization network for document image layout segementation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-11 Yujie Li; Pengfei Zhang; Xing Xu; Yi Lai; Fumin Shen; Lijiang Chen; Pengxiang Gao
Despite the great performance in layout analysis tasks made by semantic segmentation, they usually need a large number of annotated images for training and are difficult to learn a new category which is absent in the training categories. Meta-learning and few-shot segmentation have been developed to solve the above two difficulties. In this paper, we propose a novel method dubbed Few-Shot Prototype
-
Pedestrian detection with super-resolution reconstruction for low-quality image Pattern Recogn. (IF 7.196) Pub Date : 2021-02-14 Yi Jin; Yue Zhang; Yigang Cen; Yidong Li; Vladimir Mladenovic; Viacheslav Voronin
Pedestrian detection has emerged as a fundamental technology for autonomous cars, robotics, pedestrian search, and other applications. Although many excellent object detection algorithms can be used for pedestrian detection, it is still a challenging problem due to the complicated real-world scenarios, e.g., the detection of pedestrians in low-quality surveillance videos. In this paper, we aim to study
-
Residual Multi-Task Learning for Facial Landmark Localization and Expression Recognition Pattern Recogn. (IF 7.196) Pub Date : 2021-02-20 Boyu Chen; Wenlong Guan; Peixia Li; Naoki Ikeda; Kosuke Hirasawa; Huchuan Lu
Facial landmark localization and expression recognition are two important and highly relevant topics in facial analysis. However, few works focus on using the complementary information between the two tasks to improve the performance. In this paper, we propose a residual multi-task learning framework to predict the two tasks simultaneously. Different from previous multi-task learning methods which
-
Scalable multi-label canonical correlation analysis for cross-modal retrieval Pattern Recogn. (IF 7.196) Pub Date : 2021-02-20 Xin Shu; Guoying Zhao
Multi-label canonical correlation analysis (ml-CCA) has been developed for cross-modal retrieval. However, the computation of ml-CCA involves dense matrices eigendecomposition, which can be computationally expensive. In addition, ml-CCA only takes semantic correlation into account which ignores the cross-modal feature correlation. In this paper, we propose a novel framework to simultaneously integrate
-
Fooling Deep Neural Detection Networks with Adaptive Object-oriented Adversarial Perturbation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-20 Yatie Xiao; Chi-Man Pun; Bo Liu
Deep learning has shown superiority in dealing with complicated and professional tasks (e.g., computer vision, audio, and language processing). However, research works have confirmed that Deep Neural Networks (DNNs) are vulnerable to carefully crafted adversarial perturbations, which cause DNNs confusion on specific tasks. In object detection domain, the background has little contributions to object
-
Skeletonisation Algorithms with Theoretical Guarantees for Unorganised Point Clouds with High Levels of Noise Pattern Recogn. (IF 7.196) Pub Date : 2021-02-20 P. Smith; V. Kurlin
Data Science aims to extract meaningful knowledge from unorganised data. Real datasets usually come in the form of a cloud of points. It is a requirement of numerous applications to visualise an overall shape of a noisy cloud of points sampled from a non-linear object that is more complicated than a union of disjoint clusters. The skeletonisation problem in its hardest form is to find a 1-dimensional
-
FleBiC: Learning classifiers from high-dimensional biomedical data using discriminative biclusters with non-constant patterns Pattern Recogn. (IF 7.196) Pub Date : 2021-02-20 Rui Henriques; Sara C. Madeira
The discovery of discriminative patterns from high-dimensional data offers the possibility to learn from informative subspaces and pattern-centric features, paving the way to associative classifiers. Despite the success achieved by associative classifiers, such as random forests or XGBoost, they generally neglect discriminative subspaces with non-constant coherencies. Research on biclustering has for
-
Time series cluster kernels to exploit informative missingness and incomplete label information Pattern Recogn. (IF 7.196) Pub Date : 2021-02-20 Karl Øyvind Mikalsen; Cristina Soguero-Ruiz; Filippo Maria Bianchi; Arthur Revhaug; Robert Jenssen
The time series cluster kernel (TCK) provides a powerful tool for analysing multivariate time series subject to missing data. TCK is designed using an ensemble learning approach in which Bayesian mixture models form the base models. Because of the Bayesian approach, TCK can naturally deal with missing values without resorting to imputation and the ensemble strategy ensures robustness to hyperparameters
-
Face alignment using two-stage cascaded pose regression and mirror error correction Pattern Recogn. (IF 7.196) Pub Date : 2021-02-03 Ziye Tong; Junwei Zhou
Recently, a series of cascaded pose regression based facial landmark localization methods under occlusion have been proposed. However, partial occlusions and pose variations will break the entire structure of the face which poses obstacles to global regression. Moreover, there lack techniques to evaluate the reliability of the regression results during the regression process. In this paper, we propose
-
Jointly learning compact multi-view hash codes for few-shot FKP recognition Pattern Recogn. (IF 7.196) Pub Date : 2021-02-13 Lunke Fei; Bob Zhang; Jie Wen; Shaohua Teng; Shuyi Li; David Zhang
As a relatively new biometric trait, Finger-Knuckle-Print (FKP) plays a vital role in establishing a personal authentication system in modern society due to its rich discriminative features, low time cost in image capture and user-friendliness. However, most existing KFP descriptors are hand-crafted and fail to work well with limited training samples. In this paper, we propose a feature learning method
-
Geometric moment invariants to spatial transform and N-fold symmetric blur Pattern Recogn. (IF 7.196) Pub Date : 2021-02-13 Hanlin Mo; Hongxiang Hao; Hua Li
In this paper, we focus on the derivation of blur moment invariants. Blur moment invariants are image moment-based features, which preserve their values when the image is convolved by a point-spread function (PSF). Suppose a PSF has N-fold rotational symmetry, we prove its geometric moments of the same order are linearly dependent. Depending on this property, a new approach is proposed to determine
-
An adversarial human pose estimation network injected with graph structure Pattern Recogn. (IF 7.196) Pub Date : 2021-02-09 Lei Tian; Peng Wang; Guoqiang Liang; Chunhua Shen
Because of the invisible human keypoints in images caused by illumination, occlusion and overlap, it is likely to produce unreasonable human pose prediction for most of the current human pose estimation methods. In this paper, we design a novel generative adversarial network (GAN) to improve the localization accuracy of visible joints when some joints are invisible. The network consists of two simple
-
3D-CenterNet: 3D object detection network for point clouds with center estimation priority Pattern Recogn. (IF 7.196) Pub Date : 2021-02-11 Qi Wang; Jian Chen; Jianqiang Deng; Xinfang Zhang
In this paper, a single-stage 3D object detection framework, 3D-CenterNet, is proposed for accurate 3D object detection from point clouds. We find that the center position is more critical for accurate bounding box detection than the other two parameters, the size and the orientation. Motivated by this discovery, we propose the center regression module (CRM) to regress the centers’ location from the
-
Brain segmentation based on multi-atlas and diffeomorphism guided 3D fully convolutional network ensembles Pattern Recogn. (IF 7.196) Pub Date : 2021-02-18 Jiong Wu; Xiaoying Tang
In this study, we proposed and validated a multi-atlas and diffeomorphism guided 3D fully convolutional network (FCN) ensemble model (M-FCN) for segmenting brain anatomical regions of interest (ROIs) from structural magnetic resonance images (MRIs). A novel multi-atlas and diffeomorphism based encoding block and ROI patches with adaptive sizes were used. In the multi-atlas and diffeomorphism based
-
Boundary-induced and Scene-aggregated Network for Monocular Depth Prediction Pattern Recogn. (IF 7.196) Pub Date : 2021-02-18 Feng Xue; Junfeng Cao; Yu Zhou; Fei Sheng; Yankai Wang; Anlong Ming
Monocular depth prediction is an important task in scene understanding. It aims to predict the dense depth of a single RGB image. With the development of deep learning, the performance of this task has made great improvements. However, two issues remain unresolved: (1) The deep feature encodes the wrong farthest region in a scene, which leads to a distorted 3D structure of the predicted depth; (2)
-
An efficient computational algorithm for Hausdorff distance based on points-ruling-out and systematic random sampling Pattern Recogn. (IF 7.196) Pub Date : 2021-02-02 Jegoon Ryu; Sei-ichiro Kamata
This paper proposes a novel algorithm for fast and accurate Hausdorff distance (HD) computation. The Hausdorff distance is used to measure the similarity between two point sets in various applications. However, it is hard to compute the HD algorithm efficiently between very large-scale point sets while ensuring the accuracy of the HD. The directed HD algorithm has two loops (called the outer loop and
-
Robust and Discriminative Image Representation: Fractional-order Jacobi-Fourier Moments Pattern Recogn. (IF 7.196) Pub Date : 2021-02-17 Hongying Yang; Shuren Qi; Jialin Tian; Panpan Niu; Xiangyang Wang
Robust and discriminative image representation is a long-lasting battle in the computer vision and pattern recognition. Moment-based image representation model is effective in satisfying the core conditions of semantic description, due to its geometric invariance and independence. However, moment-based descriptors suffer from a contradiction between the robustness and discriminability, which limits
-
A Novel Consensus Learning Approach to Incomplete Multi-view Clustering Pattern Recogn. (IF 7.196) Pub Date : 2021-02-17 Jianlun Liu; Shaohua Teng; Lunke Fei; Wei Zhang; Xiaozhao Fang; Zhuxiu Zhang; Naiqi Wu
Multi-view data may lose some instances in real applications. Most existing methods for clustering such incomplete multi-view data still have at least one of the following limitations: 1) The common relations among data points across all views are ignored. 2) The complementary multi-view information of original data representation is not well exploited. 3) Arbitrary incomplete scenarios or data with
-
A survey on matching strategies for boundary image comparison and evaluation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-17 C. Lopez-Molina; C. Marco-Detchart; H. Bustince; B. De Baets
Most of the strategies for boundary image evaluation involve the comparison of computer-generated images with ground truth solutions. While this can be done in different manners, recent years have seen a dominance of techniques based on the use of confusion matrices. That is, techniques that, at the evaluation stage, interpret boundary detection as a classification problem. These techniques require
-
GuessWhich? Visual dialog with attentive memory network Pattern Recogn. (IF 7.196) Pub Date : 2021-01-14 Lei Zhao; Xinyu Lyu; Jingkuan Song; Lianli Gao
Visual dialog is a task that two agents: Question-BOT (Q-BOT) and Answer-BOT (A-BOT), which communicate in natural language on the situation of information asymmetry. Q-BOT generates questions based on an image caption and a historical dialog. A-BOT answers the questions grounded on the image. Moreover, we play a cooperative ‘image guessing’ game between Q-BOT and A-BOT, so that Q-BOT can select an
-
An End-to-end Framework for Unconstrained Monocular 3D Hand Pose Estimation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-16 Sanjeev Sharma; Shaoli Huang
This work addresses the challenging problem of unconstrained 3D hand pose estimation using monocular RGB images. Most of the existing approaches assume some prior knowledge of hand (such as hand locations and side information) is available for 3D hand pose estimation. This restricts their use in unconstrained environments. Therefore, we present an end-to-end framework that robustly predicts hand prior
-
Practical Globally Optimal Consensus Maximization by Branch-and-Bound based on Interval Arithmetic Pattern Recogn. (IF 7.196) Pub Date : 2021-02-16 Yiru Wang; Yinlong Liu; Xuechen Li; Chen Wang; Manning Wang; Zhijian Song
Consensus maximization is widely used in robust model fitting, and it is usually solved by RANSAC-type methods in practice. However, these methods cannot guarantee global optimality and sometimes return the wrong solutions. A series of Branch-and-bound (BnB) based globally optimal methods have been proposed, most of which involve deriving a complex bound. Interval arithmetic was utilized to derive
-
Tight lower bounds for Dynamic Time Warping Pattern Recogn. (IF 7.196) Pub Date : 2021-02-16 Geoffrey I. Webb; François Petitjean
Dynamic Time Warping (DTW) is a popular similarity measure for aligning and comparing time series. Due to DTW’s high computation time, lower bounds are often employed to screen poor matches. Many alternative lower bounds have been proposed, providing a range of different trade-offs between tightness and computational efficiency. LB_KEOGH provides a useful trade-off in many applications. Two recent
-
Learning deep discriminative embeddings via joint rescaled features and log-probability centers Pattern Recogn. (IF 7.196) Pub Date : 2021-01-27 Huayue Cai; Xiang Zhang; Long Lan; Guohua Dong; Chuanfu Xu; Xinwang Liu; Zhigang Luo
Recently softmax based loss functions have surged to advance image classification and face verification. Most efforts boost discrimination of the softmax loss by using novel angular margins in varying ways, but few analyze where the discrimination truly comes from whilst considering the power of relieving the overfitting to enhance the softmax loss. In this paper, we firstly delve into such mainstream
-
Assessing partially ordered clustering in a multicriteria comparative context Pattern Recogn. (IF 7.196) Pub Date : 2021-01-29 Jean Rosenfeld; Yves De Smet; Olivier Debeir; Christine Decaestecker
This study considers the task of clustering for data characterized by peculiar quantitative features in that they express performance according to different indicators or criteria. Performance is supposed to be optimized in one way or the other, i.e. maximized or minimized. This peculiar type of data introduces a comparative context that is not generally taken into account in the field of pattern recognition
-
Refining a k-nearest neighbor graph for a computationally efficient spectral clustering Pattern Recogn. (IF 7.196) Pub Date : 2021-02-06 Mashaan Alshammari; John Stavrakakis; Masahiro Takatsuka
Spectral clustering became a popular choice for data clustering for its ability of uncovering clusters of different shapes. However, it is not always preferable over other clustering methods due to its computational demands. One of the effective ways to bypass these computational demands is to perform spectral clustering on a subset of points (data representatives) then generalize the clustering outcome
-
Online Anomaly Detection in Surveillance Videos with Asymptotic Bounds on False Alarm Rate Pattern Recogn. (IF 7.196) Pub Date : 2021-02-01 Keval Doshi; Yasin Yilmaz
Anomaly detection in surveillance videos is attracting an increasing amount of attention. Despite the competitive performance of recent methods, they lack theoretical performance analysis, particularly due to the complex deep neural network architectures used in decision making. Additionally, online decision making is an important but mostly neglected factor in this domain. Much of the existing methods
-
A new EM algorithm for flexibly tied GMMs with large number of components Pattern Recogn. (IF 7.196) Pub Date : 2021-01-22 Hadi Asheri; Reshad Hosseini; Babak Nadjar Araabi
Gaussian mixture models (GMMs) are a family of generative models used extensively in many machine learning applications. The modeling power of GMMs is directly linked to the number of components. Memory, computational load and lack of enough data hinders using GMMs with large number of components. To tackle this problem, GMMs with a tying scheme that we call flexibly tied GMM was proposed in the literature
-
Multi-task contrastive learning for automatic CT and X-ray diagnosis of COVID-19 Pattern Recogn. (IF 7.196) Pub Date : 2021-01-26 Jinpeng Li; Gangming Zhao; Yaling Tao; Penghua Zhai; Hao Chen; Huiguang He; Ting Cai
Computed tomography (CT) and X-ray are effective methods for diagnosing COVID-19. Although several studies have demonstrated the potential of deep learning in the automatic diagnosis of COVID-19 using CT and X-ray, the generalization on unseen samples needs to be improved. To tackle this problem, we present the contrastive multi-task convolutional neural network (CMT-CNN), which is composed of two
-
Quaternionic extended local binary pattern with adaptive structural pyramid pooling for color image representation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-13 Tiecheng Song; Liangliang Xin; Chenqiang Gao; Tianqi Zhang; Yao Huang
This paper proposes a novel feature representation method for color images, namely quaternionic extended local binary pattern (QxLBP) with adaptive structural pyramid pooling (ASPP). First, we propose a QxLBP operator to encode local neighboring information and complementary modulus and phase information in the quaternion domain of color images. In QxLBP, an extended quaternionic representation (EQR)
-
A Hierarchical Sampling Based Triplet Network for Fine-grained Image Classification Pattern Recogn. (IF 7.196) Pub Date : 2021-02-13 Guiqing He; Feng Li; Qiyao Wang; Zongwen Bai; Yuelei Xu
Deep metric learning leverages well-designed distance measurement and a sample selection strategy to learn a discriminative feature space. Among the various deep metric learning formulations, triplet loss is built based on a 3-tuple that can simultaneously minimise the distance between the items in the positive pair and maximise the distance between those in the negative pair. However, this endeavour
-
LCU-Net: A Novel Low-cost U-Net for Environmental Microorganism Image Segmentation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-13 Jinghua Zhang; Chen Li; Sergey Kosov; Marcin Grzegorzek; Kimiaki Shirahama; Tao Jiang; Changhao Sun; Zihan Li; Hong Li
In this paper, we propose a novel Low-cost U-Net (LCU-Net) for the Environmental Microorganism (EM) image segmentation task to assist microbiologists in detecting and identifying EMs more effectively. The LCU-Net is an improved Convolutional Neural Network (CNN) based on U-Net, Inception, and concatenate operations. It addresses the limitation of single receptive field setting and the relatively high
-
Discriminative shared transform learning for sketch to image matching Pattern Recogn. (IF 7.196) Pub Date : 2021-01-12 Shruti Nagpal; Maneet Singh; Richa Singh; Mayank Vatsa
Sketch to digital image matching refers to the problem of matching a sketch image (often drawn by hand or created by a software) against a gallery of digital images (captured via an acquisition device such as a digital camera). Automated sketch to digital image matching has applicability in several day to day tasks such as similar object image retrieval, forensic sketch matching in law enforcement
-
Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network Pattern Recogn. (IF 7.196) Pub Date : 2021-02-02 Weijie Sheng; Xinde Li
Human gait conveys significant information that can be used for identity recognition and emotion recognition. Recent studies have focused more on gait identity recognition than emotion recognition and regarded these two recognition tasks as independent and unrelated. How to train a unified model to effectively recognize the identity and emotion from gait at the same time is a novel and challenging
-
Deep ancient Roman Republican coin classification via feature fusion and attention Pattern Recogn. (IF 7.196) Pub Date : 2021-02-03 Hafeez Anwar; Saeed Anwar; Sebastian Zambanini; Fatih Porikli
We perform the classification of ancient Roman Republican coins via recognizing their reverse motifs where various objects, faces, scenes, animals, and buildings are minted along with legends. Most of these coins are eroded due to their age and varying degrees of preservation, thereby affecting their informative attributes for visual recognition. Changes in the positions of principal symbols on the
-
Multi-task face analyses through adversarial learning Pattern Recogn. (IF 7.196) Pub Date : 2021-01-26 Shangfei Wang; Shi Yin; Longfei Hao; Guang Liang
The inherent relations among multiple face analysis tasks, such as landmark detection, head pose estimation, gender recognition and face attribute estimation are crucial to boost the performance of each task, but have not been thoroughly explored since typically these multiple face analysis tasks are handled as separate tasks. In this paper, we propose a novel deep multi-task adversarial learning method
-
Dual space latent representation learning for unsupervised feature selection Pattern Recogn. (IF 7.196) Pub Date : 2021-02-02 Ronghua Shang; Lujuan Wang; Fanhua Shang; Licheng Jiao; Yangyang Li
In real-world applications, data instances are not only related to high-dimensional features, but also interconnected with each other. However, the interconnection information has not been fully exploited for feature selection. To address this issue, we propose a novel feature selection algorithm, called dual space latent representation learning for unsupervised feature selection (DSLRL), which exploits
-
Memetic differential evolution methods for clustering problems Pattern Recogn. (IF 7.196) Pub Date : 2021-01-27 Pierluigi Mansueto; Fabio Schoen
The Euclidean Minimum Sum-of-Squares Clustering(MSSC) is one of the most important models for the clustering problem. Due to its NP-hardness, the problem continues to receive much attention in the scientific literature and several heuristic procedures have been proposed. Recent research has been devoted to the improvement of the classical K-MEANS algorithm, either by suitably selecting its starting
-
Learning Robust Feature Transformation for Domain Adaptation Pattern Recogn. (IF 7.196) Pub Date : 2021-02-05 Wei Wang; Hao Wang; Zhi-Yong Ran; Ran He
There is a growing importance of feature extraction in transferring valuable knowledge from a source domain to a different but related target domain. However, when the target data are contaminated by unpredictable and complex noises, the ability of most existing feature extraction methods would be limited. In this paper, we deeply investigate the robust property of Kernel Mean P-Power Error Loss (KMPE-Loss)
-
Joint stroke classification and text line grouping in online handwritten documents with edge pooling attention networks Pattern Recogn. (IF 7.196) Pub Date : 2021-02-02 Jun-Yu Ye; Yan-Ming Zhang; Qing Yang; Cheng-Lin Liu
Stroke classification and text line grouping are important tasks in online handwritten document segmentation. In the past, the two tasks were usually performed using different models which are trained independently and perform sequentially. This cannot optimize the integration of contextual information and the system may suffer from error accumulation in stroke classification. In this paper, we propose
-
Optical flow and scene flow estimation: A survey Pattern Recogn. (IF 7.196) Pub Date : 2021-02-01 Mingliang Zhai; Xuezhi Xiang; Ning Lv; Xiangdong Kong
Motion analysis is one of the most fundamental and challenging problems in the field of computer vision, which can be widely applied in many areas, such as autonomous driving, action recognition, scene understanding, and robotics. In general, the displacement field between subsequent frames can be divided into two types: optical flow and scene flow. The optical flow represents the pixel motion of adjacent
-
Internet financing credit risk evaluation using multiple structural interacting elastic net feature selection Pattern Recogn. (IF 7.196) Pub Date : 2021-01-26 Lixin Cui; Lu Bai; Yanchao Wang; Xin Jin; Edwin R. Hancock
Internet financing is an important alternative to banks where individuals or SMEs borrow money using online trading platforms. A central problem for internet financing is how to identify the most influential factors that are closely related to the credit risks. This problem is inherently challenging because the raw data of internet financing is often associated with complex structural correlations
-
Automatic analysis of artistic paintings using information-based measures Pattern Recogn. (IF 7.196) Pub Date : 2021-02-01 Jorge Miguel Silva; Diogo Pratas; Rui Antunes; Sérgio Matos; Armando J. Pinho
The artistic community is increasingly relying on automatic computational analysis for authentication and classification of artistic paintings. In this paper, we identify hidden patterns and relationships present in artistic paintings by analysing their complexity, a measure that quantifies the sum of characteristics of an object. Specifically, we apply Normalized Compression (NC) and the Block Decomposition
-
Thermodynamic motif analysis for directed stock market networks Pattern Recogn. (IF 7.196) Pub Date : 2021-02-02 Dongdong Chen; Xingchen Guo; Jianjia Wang; Jiatong Liu; Zhihong Zhang; Edwin R. Hancock
In this paper, we present a novel thermodynamically based analysis method for directed networks, and in particular for time-evolving networks in the finance domain. Based on an analogy with a dilute gas in statistical mechanics, we develop a partition function for a network composed of directed motifs. The method relies on the decomposition of directed networks into a series of frequently occurring
-
Bound estimation-based safe acceleration for maximum margin of twin spheres machine with pinball loss Pattern Recogn. (IF 7.196) Pub Date : 2021-02-01 Min Yuan; Yitian Xu
Maximum margin of twin spheres support vector machine (MMTSSVM) is an efficient method for imbalanced data classification. As an extension to enhance noise insensitivity of MMTSSVM, MMTSSVM with pinball loss (Pin-MMTSM) has a good generalization performance. However, it is not efficient enough for large-scale data. Inspired by the sparse solution of SVMs, in this paper, we propose a safe accelerative
-
Hierarchical distillation learning for scalable person search Pattern Recogn. (IF 7.196) Pub Date : 2021-02-01 Wei Li; Shaogang Gong; Xiatian Zhu
Existing person search methods typically focus on improving person detection accuracy. This ignores the model inference efficiency, which however is fundamentally significant for real-world applications. In this work, we address this limitation by investigating the scalability problem of person search involving both model accuracy and inference efficiency simultaneously. Specifically, we formulate
-
Spatial context-aware network for salient object detection Pattern Recogn. (IF 7.196) Pub Date : 2021-02-02 Yuqiu Kong; Mengyang Feng; Xin Li; Huchuan Lu; Xiuping Liu; Baocai Yin
Salient Object Detection (SOD) is a fundamental problem in the field of computer vision. This paper presents a novel Spatial Context-Aware Network (SCA-Net) for SOD in images. Compared with other recent deep learning based SOD algorithms, SCA-Net can more effectively aggregate multi-level deep features. A Long-Path Context Module (LPCM) is employed to grant better discrimination ability to feature
-
Automatic medical image interpretation: State of the art and future directions Pattern Recogn. (IF 7.196) Pub Date : 2021-01-29 Hareem Ayesha; Sajid Iqbal; Mehreen Tariq; Muhammad Abrar; Muhammad Sanaullah; Ishaq Abbas; Amjad Rehman; Muhammad Farooq Khan Niazi; Shafiq Hussain
Automatic Natural language interpretation of medical images is an emerging field of Artificial Intelligence (AI). The task combines two fields of AI; computer vision and natural language processing. This is a challenging task that goes beyond object detection, segmentation, and classification because it also requires the understanding of the relationship between different objects of an image and the
-
Multi-task learning for simultaneous script identification and keyword spotting in document images Pattern Recogn. (IF 7.196) Pub Date : 2021-01-18 Ahmed Cheikhrouhou; Yousri Kessentini; Slim Kanoun
In this paper, an end-to-end multi-task deep neural network was proposed for simultaneous script identification and Keyword Spotting (KWS) in multi-lingual hand-written and printed document images. We introduced a unified approach which addresses both challenges cohesively, by designing a novel CNN-BLSTM architecture. The script identification stage involves local and global features extraction to
-
Change-point detection in hierarchical circadian models Pattern Recogn. (IF 7.196) Pub Date : 2021-01-13 Pablo Moreno-Muñoz; David Ramírez; Antonio Artés-Rodríguez
This paper addresses the problem of change-point detection in sequences of high-dimensional and heterogeneous observations, which also possess a periodic temporal structure. Due to the dimensionality problem, when the time between change points is of the order of the dimension of the model parameters, drifts in the underlying distribution can be misidentified as changes. To overcome this limitation
-
Inferring spatial relations from textual descriptions of images Pattern Recogn. (IF 7.196) Pub Date : 2021-01-27 Aitzol Elu; Gorka Azkune; Oier Lopez de Lacalle; Ignacio Arganda-Carreras; Aitor Soroa; Eneko Agirre
Generating an image from its textual description requires both a certain level of language understanding and common sense knowledge about the spatial relations of the physical entities being described. In this work, we focus on inferring the spatial relation between entities, a key step in the process of composing scenes based on text. More specifically, given a caption containing a mention to a subject
Contents have been reproduced by permission of the publishers.