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

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]

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

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

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

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

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

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 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

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 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

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

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

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

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

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

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

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

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

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

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

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

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

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)

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 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

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

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

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

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

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

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

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

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

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

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

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

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

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)

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

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

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

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

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

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

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

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

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)

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

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 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

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

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

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

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

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 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

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

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

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