Unreliable Ones Research Articles

A Survey on Recommender Systems Using Graph Neural Network

The expansion of the Internet has resulted in a change in the flow of information. With the vast amount of digital information generated online, it is easy for users to feel overwhelmed. Finding the specific information can be a challenge, and it can be difficult to distinguish credible sources from unreliable ones. This has made recommender system (RS) an integral part of the information services framework. These systems alleviate users from information overload by analyzing users’ past preferences and directing only desirable information toward users. Traditional RSs use approaches like collaborative and content-based filtering to generate recommendations. Recently, these systems have evolved to a whole new level, intuitively optimizing recommendations using deep network models. graph neural networks (GNNs) have become one of the most widely used approaches in RSs, capturing complex relationships between users and items using graphs. In this survey, we provide a literature review of the latest research efforts done on GNN-based RSs. We present an overview of RS, discuss its generalized pipeline and evolution with changing learning approaches. Furthermore, we explore basic GNN architecture and its variants used in RSs, their applications, and some critical challenges for future research.

Sexual Information Sources And Risky Sexual Behaviour Among Female Secondary School Adolescents In Calabar Municipality, Cross River State, Nigeria

This study adopted correlational survey design to establish the relationship between sexual information sources and risky sexual behaviour among female secondary school adolescents in Calabar Municipality, Cross River State, Nigeria. It was guided by two research questions and two null hypotheses. A sample of 395 female students in public secondary schools in the study area were selected using purposive and simple random sampling techniques. One instrument titled “sexual information sources and risky sexual behaviour (SISRSBQ) was developed by the researcher with the help of research experts and used for data collection. The reliability of the questionnaire, established using Cronbach Alpha which ranges from 80 to .87. The hypotheses were tested using Pearson Product Moment Correlation Coefficient at .05 level of significance. The findings of the study revealed that formal education, social media sources of information significantly relate to risky sexual behaviour among female secondary school adolescents. it was concluded that the risky sexual behaviours of female students depend their formal education, social media sources of information. Based on the findings and conclusion of this study, it was recommended amongst others that schools should develop curricula that not only provide accurate sexual health information but also teach critical media literacy skills. This would help students discern credible sources from unreliable ones on social media platforms.

Semi-supervised segmentation of medical images focused on the pixels with unreliable predictions

Pseudo-labeling is a well-studied approach in semi-supervised learning. However, unreliable or potentially incorrect pseudo-labels can accumulate training errors during iterative self-training steps, leading to unstable performance. Addressing this challenge typically involves either discarding unreliable pseudo-labels, resulting in the loss of important data, or attempting to refine them, risking the possibility of worsening the pseudo-labels in some cases/pixels. In this paper, we propose a novel method based on pseudo-labeling for semi-supervised segmentation of medical images. Unlike existing approaches, our method neither discards any data nor worsens reliable pseudo-labels. Our approach generates uncertainty masks for the predictions, utilizing reliable pixels without any modification as ground truths and modifying the unreliable ones rather than discarding them. Furthermore, we introduce a novel loss function that incorporates both mentioned parts by multiplying each term by its corresponding uncertainty mask, encompassing reliable and unreliable pixels. The reliable pixels are addressed using a masked cross-entropy loss function, while the modification of the unreliable pixels is performed through a deep-learning-based adaptation of active contours. The entire process is solved within a single loss function without the need to solve traditional active contour equations. We evaluated our approach on three publicly available datasets, including MRI and CT images from cardiac structures and lung tissue. Our proposed method outperforms the state-of-the-art semi-supervised learning methods on all three datasets. Implementation of our work is available at https://github.com/behnam-rahmati/Semi-supervised-medical.

Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and re-generates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://github.com/kwwcv/SSMP.

Redundant co-training: Semi-supervised segmentation of medical images using informative redundancy

Pseudo-labeling, consistency regularization, and co-training are common paradigms for semi-supervised learning. In this paper, we propose a novel method based on co-training and pseudo-labeling for the semi-supervised segmentation of the left ventricle. Our co-training strategy is novel and unlike most previous works does not rely on using multiple-view datasets, performing weak/strong augmentations on the input images or perturbations on the networks. We proposed creating redundant labels by utilizing the provided ground-truths and training networks segmenting different overlapping regions corresponding to the created labels. Although the new labels seem to be redundant, we demonstrated that they provide valuable information to the networks. The predictions of the redundant networks (which are trained on the redundant labels) can be used in the pixels where the primary network’s predictions are not reliable. This enables extracting a secondary source of information without requiring any additional ground-truths. The common practice in pseudo-labeling is using the reliable predictions of the unlabeled data and discarding the unreliable ones. However, we proposed utilizing predictions from the redundant networks to generate pseudo-labels for the unreliable pixels in the primary network’s predictions, rather than simply discarding them. We validated our method on two left ventricle segmentation datasets, and it surpassed the state-of-the-art semi-supervised learning approaches. Furthermore, we conducted extensive studies to analyze the proposed method from different aspects. Implementation of our work is available at https://github.com/behnam-rahmati/redundant-cotraining.

Discriminative subspace embedded dynamic geometrical and statistical alignment based on pseudo-label correction for cross-domain bearing fault diagnosis

Many domain adaptation (DA) approaches have been developed to address the challenge of domain divergence in cross-domain fault diagnosis. However, most of them only attempt to align statistical distribution while neglecting geometric alignment between source and target data. Furthermore, the use of some unreliable pseudo-labels may cause geometrical and statistical distributions mismatching and interfere with the DA model generating correct pseudo-labels during the iterative learning. In this paper, we propose a new model called discriminative subspace embedded dynamic geometrical and statistical alignment based on pseudo-label correction (DSDGSA-PC) for bearing fault diagnosis. Firstly, discriminative subspace alignment is proposed to mitigate feature redundancy and divergence by generating aligned subspaces for two domains, while preserving class discriminative information and global structures of data. Then, DSDGSA-PC leverages the representer theorem and the principle of structural risk minimization to learn a domain-invariant classifier in the subspace, while minimizing statistical and geometrical shift by jointly optimizing dynamic graph embedding and dynamic weighted distribution alignment strategies. Finally, a novel pseudo-label correction mechanism is integrated into DSDGSA-PC to evaluate the credibility of pseudo-labels and rectify the unreliable ones during the iterations. The experimental results illustrate that DSDGSA-PC has higher transfer performance compared to several advanced methods on 24 transfer tasks.

Facial Expression Recognition with Contrastive Learning and Uncertainty-Guided Relabeling

Facial expression recognition (FER) plays a vital role in the field of human-computer interaction. To achieve automatic FER, various approaches based on deep learning (DL) have been presented. However, most of them lack for the extraction of discriminative expression semantic information and suffer from the problem of annotation ambiguity. In this paper, we propose an elaborately designed end-to-end recognition network with contrastive learning and uncertainty-guided relabeling, to recognize facial expressions efficiently and accurately, as well as to alleviate the impact of annotation ambiguity. Specifically, a supervised contrastive loss (SCL) is introduced to promote inter-class separability and intra-class compactness, thus helping the network extract fine-grained discriminative expression features. As for the annotation ambiguity problem, we present an uncertainty estimation-based relabeling module (UERM) to estimate the uncertainty of each sample and relabel the unreliable ones. In addition, to deal with the padding erosion problem, we embed an amending representation module (ARM) into the recognition network. Experimental results on three public benchmarks demonstrate that our proposed method facilitates the recognition performance remarkably with 90.91% on RAF-DB, 88.59% on FERPlus and 61.00% on AffectNet, outperforming current state-of-the-art (SOTA) FER methods. Code will be available at http//github.com/xiaohu-run/fer_supCon .

KUFAH'S JUDGES IN THE SECOND ABBASID PERIOD ( 232-334/846-945)

Objectives: This study aims to know what the nature of Kufah’s judges, and the authority of appointing them in the second Abbasid period. It also aims to clarify their characteristics, qualifications, specializations, doctrines, ethnic origins, social backgrounds, and their relations with the Caliph and the various administrative bodies. Methodology: In Kufah, 18 judges were counted in a specific period of time, and by tracing their lives in the primary sources, their biographies were studied and the common points between them were explored to reach the results according to the historical research method. The primary material was collected from its original sources, the novels were compared and analyzed, then the positive internal criticism was applied. Then sorting them out, excluding the unreliable ones, subjecting the reliable ones to negative internal criticism, and then formulating the historical material. Results: The results of the study show that the judiciary in the first Abbasid period was an official religious institution, and the choice of who would take over was one of the competences of the Caliph, regardless of the influences he was subject to or the consultations and opinions he might hear when choosing any judge. The results of this study also show the qualities and qualifications of judges. These qualifications may differ from one judge to another, but in their entirety they emphasize good qualities and high qualifications. Their knowledge was not limited to the sciences of the Arabic language and its literature, history and genealogy, but the religious sciences were among the most important sciences that the judges were keen to acquire, so most of them were scholars of Hadith and jurists, who belonged to different schools of thought: six of them were Hanafi judges, two were Shafi’i judges, and two were Maliki. The three Sunni doctrine prevailed in Kufah, and the Hanbali doctrine was absent there. Among the results of this study is the strength and rigor of the judge's exercise of his authority and the breadth and diversity of his competences. In addition to the purely judicial tasks, some of them practiced work of a judicial or non-judicial nature. As for the social backgrounds of the Kufah’s judges, their origins were diverse, dating back to different cities and multiple families. The origins of two of the eighteen judges of Kufah were of Ajami origins, and the rest were descended from different Arab tribes. Conclusion: Like the rest of the cities of the Abbasid Caliphate, the judge of Kufah enjoyed a decent position that enabled him to practice his work under clear sovereignty that contributed to the application of rulings to the people of Kufah away from the interference of the administrative authority in the state

SentiStory: A Multi-Layered Sentiment-Aware Generative Model for Visual Storytelling

The visual storytelling (VIST) task aims at generating reasonable, human-like and coherent stories with the image streams as input. Although many deep learning models have achieved promising results, most of them do not directly leverage the sentiment information of stories. In this paper, we propose a sentiment-aware generative model for VIST called SentiStory. The key of SentiStory is a multi-layered sentiment extraction module (MLSEM). For a given image stream, the higher layer gives coarse-grained but accurate sentiments, while the lower layer of the MLSEM extracts fine-grained but usually unreliable ones. The two layers are combined strategically to generate coherent and rich visual sentiment concepts for the VIST task. Results from both automatic and human evaluations demonstrate that with the help of the MLSEM, SentiStory achieves improvement in generating more coherent and human-like stories.

A multistage retrieval system for health-related misinformation detection

Web search is widely used to find online medical advice. As such, health-related information access requires retrieval algorithms capable of promoting reliable documents and filtering out unreliable ones. To this end, different types of components, such as query-document matching features, passage relevance estimation and AI-based reliability estimators, need to be combined. In this paper, we propose an entire pipeline for misinformation detection, based on the fusion of multiple content-based features. We present experiments which study the influence of each pipeline stage for the target task.Our technological solution incorporates signals from technologies derived from diverse research fields, including search, deep learning for natural language processing, as well as advanced supervised and unsupervised learning. To combine evidence, different score fusion strategies are compared, including unsupervised rank fusion techniques and learning-to-rank methods. The reference framework for empirically validating our solution is the TREC Health Misinformation Track, which provides several challenging subtasks that foster research on the identification of reliable and correct information for health-related decision making tasks. More specifically, we address a total recall task, the goal of which is to identify all the documents conveying incorrect information for a specific set of topics, and an ad-hoc retrieval task, aiming to rank credible and correct information over incorrect information. All variants are evaluated with an assorted set of effectiveness metrics, which includes standard search measures, such as R-Precision, Average Precision or Normalised Discounted Cumulative Gain, and innovative metrics based on the compatibility between the ranked output and two reference rankings composed of helpful and harmful documents, respectively.Our experiments demonstrate the effectiveness of the proposed pipeline stages and indicate that sophisticated supervised fusion methods do not fare better than simpler fusion alternatives. Additionally, for reliability estimation, unsupervised textual similarity performs better than textual classification based on supervised learning. The results also show that the presented approach is highly competitive when compared with state-of-the-art solutions for the same problem.

A unified probabilistic framework of robust and efficient color consistency correction for multiple images

The task of color consistency correction for multiple images mainly arises from applications like orthoimage producing, panoramic image stitching and 3D reconstruction. In these applications, images usually have been geometrically aligned. So correspondences can be easily extracted and used to solve color correction models. Almost all previous methods assume that the color residuals of correspondences follow Gaussian distribution and solve color models based on least squares. However, correspondences often contain unreliable ones due to altered areas and misalignments, which results in unusual large color residuals, namely, outliers. Imposing color consistency constaints on unreliable correspondences significantly affects the performance of color correction since Gaussian is highly sensitive to outliers. In this paper, to solve this problem theoretically, we first propose a unified probabilistic framework that formulates global color correction as a maximum posteriori probability (MAP) estimation. It is flexible enough to allow for any assumptions of residual distribution. And most color correction methods can be explained in this unified framework. Then, to robust against outliers, we use t-distribution with heavier tails than Gaussian to fit the color residuals. It is more robust because higher probabilities can be assigned to outliers. We show that the MAP formulation based on t-distribution actually leads to weighted least squares, which downweights outliers adaptively. Besides, our framework requires no user-defined robustness parameter. Because all parameters of color models and t-distribution are optimized jointly. In addition, to decrease the huge computational cost of large scale dataset, we extend the proposed framework to a parallel vesion which can achieve efficiency and global optimal at the same time. In the experiments, we compare our approach with the state-of-the-art approaches of Shen et al., Xia et al., etc. on several challenging datasets with outliers. The results demonstrate that our approach achieves the best robustness (average color consistency scores CD=5.4, DeltaE2000=5.7 and PSNR=24.0) and the best efficiency (given 100 images, non-parallel/parallel runs more than 5/50 times faster than others). The implementation is available at https://github.com/yinxuanLi/ColorConsistencyCorrectionForMultipleImages.

Convolution by Multiplication: Accelerated Two- Stream Fourier Domain Convolutional Neural Network for Facial Expression Recognition

Facial expression plays an important role in human communication as a type of nonverbal language and has been widely used in various areas such as psychology, human-computer interaction and robotics. Nowadays, convolutional neural network is a promising approach for facial expression recognition. However, convolutional layers can be time-consuming and computationally expensive because a large number of parameters participate in the calculations and need to be updated during training. To improve the performance of deep neural network in facial expression recognition and accelerate training and calculation, we propose a novel framework which adopts efficient element-wise multiplication to replace traditional convolution. To disentangle reliable feature representation for more effective recognition and further enhance the recognition performance while maintaining the efficiency, we propose a representation scheme which can retain informative feature components while removing unreliable ones in Fourier domain based on the proposed multiplication framework. Extensive comparison and ablation studies are conducted on several benchmark datasets, which shows the efficiency and effectiveness of the proposed model.

Deception Attacks on Remote Estimation with Disclosure and Disruption Resources

The problem of deception attacks utilizing both disclosure and disruption resources in the multiple types of sensors setting against remote state estimation is investigated in this paper. A group of sensors, including reliable and unreliable ones, measure system states and transmit innovations to a remote fusion center via wireless channels, wherein a malicious attacker can modify the data packets of unreliable sensors. By virtue of disclosure resources of reliable sensors and disruption resources of unreliable ones, a stealthy linear attack strategy is given, which can deceive the anomaly detectors and degrade the estimation performance. We obtain feasible criteria under which such attack policies can bypass existing detectors. The evolution of estimation error covariance at the remote end under the attacks is analyzed. Then, a closed-form expression of the optimal linear deception attack maximizing estimation error covariance is derived. Moreover, extended results on the designed attack strategies and attackers with extra measurements are provided. Finally, two illustrative examples with stable and unstable processes are given to verify the effectiveness of proposed methods.

The Impact of Coronavirus Information-Seeking Behavior on Dental Care Access: A Cross-Sectional Questionnaire-Based Study.

Health information-seeking behavior provides a variety of benefits, such as reducing knowledge gaps and educating individuals outside the medical office. This study aimed at evaluating if different sources used to gather information on COVID-19 could affect the willingness to undergo dental appointments. An anonymous survey was posted on social media. The 1003 respondents used several channels of communication, clearly distinguishing reliable from unreliable ones. Multiple logistic regression estimated the effect of different information channels on the probability of being strongly influenced by COVID-19 in accessing upcoming dental appointments. Newspapers were the most-used channel of information (61.2%), blogs and forums the least used (11.2%). Overall, the more an individual was informed, the higher was the risk of missing upcoming dental care appointments (OR 2.05, CI 1.45–2.90, p < 0.001). The two most reliable channels of communication were identified in journals/websites of medicine and healthcare professionals. Women proved to be more active in gathering information and relying on less secure but more personal channels, such as social media and friends and family, thus having an increased risk of being influenced by COVID-19 information regarding upcoming dental care appointments (OR 3.62, CI 0.85–15.52, p < 0.1 and OR 1.60, CI 1.00–2.58, p < 0.1, respectively). Social media should have a greater presence on the side of medical service providers to avoid distortions of information and fake news that ultimately cause fear among citizens and compromise their health. Healthcare professionals and institutions should adapt their communication channels based on the audience they want to address to optimize the education and information of the final users.

The Impact of the COVID-19 Pandemic on College Students: An Online Survey

The COVID-19 pandemic, since its beginning in December 2019, has altered every aspect of human life. In Vietnam, the pandemic is in its fourth peak and is the most serious so far, putting Vietnam in the list of top 30 countries with the highest daily cases. In this paper, we wish to identify the magnitude of its impact on college students in Vietnam. As far as we’re concerned, college students belong to the most affected groups in the population, especially in big cities that have been hitting hard by the virus. We conducted an online survey from 31 May 2021 to 9 June 2021, asking students from four representative regions in Vietnam to describe how the pandemic has changed their lifestyle and studying environment, as well as their awareness, compliance, and psychological state. The collected answers were processed to eliminate unreliable ones then prepared for sentiment analysis. To analyze the relationship among the variables, we performed a variety of statistical tests, including Shapiro–Wilk, Mc Nemar, Mann–Whitney–Wilcoxon, Kruskal–Wallis, and Pearson’s Chi-square tests. Among 1875 students who participated, many did not embrace online education. A total of 64.53% of them refused to think that online education would be the upcoming trend. During the pandemic, nearly one quarter of students were in a negative mood. About the same number showed signs of depression. We also observed that there were increasing patterns in sleeping time, body weight, and sedentary lifestyle. However, they maintained a positive attitude toward health protection and compliance with government regulations (65.81%). As far as we know, this is the first project to conduct such a large-scale survey analysis on students in Vietnam. The findings of the paper help us take notice of financial and mental needs and perspective issues for indigent students, which contributes to reducing the pandemic’s negative effects and going forwards to a better and more sustainable life.

A New Belief-Based Incomplete Pattern Unsupervised Classification Method

The clustering of incomplete patterns is a very challenging task because the estimations may negatively affect the distribution of real centers and thus cause uncertainty and imprecision in the results. To address this problem, a new belief-based incomplete pattern unsupervised classification method (BPC) is proposed in this paper. First, the complete patterns are grouped into a few clusters by a classical soft method like fuzzy <inline-formula><tex-math notation="LaTeX">$c$</tex-math></inline-formula> -means to obtain the corresponding reliable centers and thereby are partitioned into reliable patterns and unreliable ones by an optimization method. Second, a basic classifier trained by reliable patterns is employed to classifies unreliable patterns and the incomplete patterns edited by the neighbors. In this way, most of the edited incomplete patterns can be submitted to specific clusters. Finally, some ambiguous patterns will be carefully repartitioned again by a new distance-based rule depending on the obtained reliable centers and belief functions theory. By doing this, a few patterns that are very difficult to classify between different specific clusters will be reasonably submitted to meta-cluster which can characterize the uncertainty and imprecision of the clusters due to missing values. The simulation results show that the BPC has the potential to deal with real datasets.

Methods of Improving the Reliability of Power Transistor Modules in Electric Energy Converters at the Stage of Completion

Providing high reliability of electric energy converters based on power semiconductor devices (PSDs) is the main goal of designers, manufacturers and users of such devices. There are many factors affecting reliability—namely, the PSD heat dissipation regime determined by the electric and thermal parameters of the devices, magnitude and type of load, and operating environment conditions. In most cases, an increase in the converters’ power is achieved by combining parallel connected semiconductor devices into modules, which gives rise to additional reliability problems for the devises. We propose several solutions to those problems that guarantee safe thermal operation regime of PSDs (transistors) in the modules by choosing proper transistors and discarding potentially unreliable ones according to criteria based on the devices’ thermal properties. A new method is proposed for the rapid assessment of thermal resistance of transistors when integrating them in the power modules.

A Robust Control Approach to Automated Manufacturing Systems Allowing Multitype and Multiquantity of Resources With Petri Nets

Up to now, the supervision and control of deadlock-free resource allocation has received considerable attention, particularly regarding their deadlock problems. To date, most solutions have supposed that allocated resources never fail. However, this is quite the opposite in reality since some resources may fail unexpectedly. A robust system should be resilient to such failures. In this paper, resources are divided into reliable ones and unreliable ones. On the basis of the deadlock avoidance algorithm which is proposed for the problem of deadlocks, we propose a robust control algorithm in the paradigm of systems of sequential systems with shared resources, which can acquire and release resources in a multitype and multiquantity way. It is validated to be a polynomially complex robust control algorithm by the distributivity analysis. Finally, experimental results show that the proposed approaches are effective as well as efficient in response to resource failures.

Robust Deadlock Avoidance and Control of Automated Manufacturing Systems With Assembly Operations Using Petri Nets

Deadlock resolution has been an important research topic in the field of automated manufacturing systems (AMSs). Researchers generally assume that AMS resources never break down whereas only a few resolve the issues of resource failures in the discrete-event supervision of AMSs. In fact, an AMS consists of a number of numerically controlled machines interacting with each other. The failure of resources happens unexpectedly. In this article, we allow parallel routes to use unreliable resources. Because of their powerful modeling capabilities, Petri nets are used to model the considered AMSs. By using a look-ahead control strategy, a robust supervisory control policy is developed for AMSs with assembly operations allowing resource failures. Our objective is to advance parts requiring failed resources in their remaining routes into a special position so as to release shared resources in case some unreliable resources fail. Consequently, those parts not necessarily requiring any failed resource can keep progressing all the time. The conventional methods are on the basis of monolithic and structure-oriented control specifications with centralized supervisors. Our policy can be implemented in a distributed, online, and local way. Several examples are given to elucidate our control policy clearly. Note to Practitioners —In automated manufacturing systems (AMSs), resources such as machines and tools with higher reliablity are always expensive. Sometimes, when it is not cost-effective to use resources with higher reliability, manufacturers may choose some resources with possible failures. These resources are thus considered as unreliable ones in our article. Normally, unreliable resources may fail unexpectedly. Their occurrences can lead a system to stagnation, causing unnecessary downtime, and bringing economic loss to enterprises. To resolve such stagnation issues, we develop a robust supervisory control policy to synthesize a robust liveness-enforcing supervisor for AMSs with assembly operations and unreliable resources. The supervisor can guarantee that a controlled system continues to progress without deadlock and blocking states even if some unreliable resources fail to work.

CAT: Corner Aided Tracking With Deep Regression Network

Single object tracking in visual media is an important yet challenging task. Various challenges, especially target scale variation, shape deformation and occlusion, can have large effects on the performances of trackers. Current deep regression based trackers only pay close attention to regression on the center key point of the tracking target, meanwhile employ the image pyramid based multi-scale testing method to deal with scale estimation. Such procedure can not properly handle the three challenges. We address these challenges in a principled way by the aid of auxiliary regressions on the four bounding box corners of the tracking target. In this work, we propose the novel Corner Aided Tracker with deep regression network, abbreviated as CAT. Different from RPN-based trackers, in CAT, four corners along with the center key point of the bounding box for tracking target are simultaneously obtained by five corresponding response maps. Furthermore, to robustly and accurately generate tight bounding boxes for the tracking target and collect reliable samples for online training of the network, we propose an adaptive key point selection method to select the subset of reliable key points and drop the unreliable ones, based on the qualities of their corresponding response maps as well as the constraints from shape, scale and location. We demonstrate that the regressed corners can help naturally locate the tracking target with tight bounding boxes. The challenges of scale variation, shape deformation and occlusion can be handled explicitly. The commonly used time-consuming image pyramid based multi-scale testing method can also be discarded. Extensive experiments on OTB2013, OTB2015, UAV123, LaSOT, VOT2016 and VOT2018 datasets are conducted to report new state-of-the-art performances and demonstrate the effectiveness of CAT.