In recent times, anchor-based visual object trackers have become increasingly popular due to their exceptional performance. However, they rely on preset anchor boxes that require manual tuning, which can impact the performance of the trackers and introduce hyper-parameter dependencies. To address these issues, an anchor-free Siamese tracker with multi-attention and corner detection mechanism was proposed. Additionally, a multiple attention fusion module was created to calculate the relationship between the template and the search area in different channels, thus enhancing the model's perception of environmental information. By eliminating the need for anchor points and performing direct computation, the proposed model minimizes the influence of hyper-parameters and human factors, resulting in improved overall efficiency. To showcase the effectiveness of the proposed tracker, comprehensive experiments were conducted on four challenging benchmarks, including OTB100, VOT2016, UAV123, and GOT-10k.

Defect detection on wafers holds immense significance in producing micro- and nano-semiconductors. As manufacturing processes grow in complexity, wafer maps may display a mixture of defect types, necessitating the utilization of more intricate deep learning models for effective feature learning. However, sophisticated models come with a demand for substantial computational resources. In this paper, we propose an efficient deep learning framework designed explicitly for mix-type wafer map defect pattern recognition. Our proposed model incorporates several crucial design elements, including lightweight convolutions, bottleneck residual connections, efficient channel attention mechanisms, and optimized activation functions, enabling it to learn spatial and channel features efficiently. We conduct evaluations on a real-world dataset containing 38 mixed-type defect patterns. The experimental results demonstrate that our framework maintains a high level of accuracy while possessing a compact parameter size and remarkably fast inference speed.

The continued influence effect of misinformation (CIEM) can negatively affect individuals’ reasoning and judgment processes. This research aims to enhance the correction of misinformation and foster rational judgement by investigating the internal brain mechanisms involved in the processing of the CIEM through the use of task-based functional magnetic resonance imaging combined with Granger causality analysis. Our findings demonstrate notable effective interactions in varying directions between the left inferior frontal gyrus and middle temporal gyrus during the encoding phase, and between the right anterior cingulate gyrus and left inferior occipital gyrus in the retrieval phase. These insights elucidate the roles of mental model updating and retrieval failure in the processing of CIEM, offering more granular evidence to support the differentiation in processing phases.

Representational momentum (RM) refers to the phenomenon in which an observer's judgment of the final location of a previously viewed moving target is often displaced forward in the direction of motion. This phenomenon is an adaptive mechanism that compensates for neural processing delays and is closely associated with visual cortex function. However, the impact of age-related decline of visual cortex function on the manifestations of RM remains unclear. The present study examined differences in the RM effect between older (N = 82) and younger adults (N = 74) using a cursor-positioning task. Additionally, resting-state functional magnetic resonance imaging was used to explore the potential neural substrates that underlie these differences, employing amplitude of low-frequency fluctuation (ALFF, reflecting the intensity of neural activity) and regional homogeneity (ReHo, reflecting the synchronization of neural activity) as indicators. Our findings indicate a significant increase in RM among older adults compared with younger adults. Neuroimaging data revealed a significant decrease in ALFF and ReHo within extensive regions of the visual cortex in older adults, validating age-related differences in this cortical area. More importantly, ALFF values in the bilateral visual area 3 and ReHo values in the bilateral visual area 2 in older adults exhibited a strong negative correlation with their RM effects. These results suggest that larger RM in older adults may be functional compensation for aging of the visual cortex.

比起新的信息,重复接触过的信息会被认为更真实,这一效应称为虚假真实效应(Illu-sory-truth effect).本文对这一效应的几种理论解释进行了比较,认为加工流畅性——认知加工过程中体验到的轻松体验——是最基础、最简洁的解释,并从加工流畅性产生的条件、原因、与情感的联系、神经基础方面进一步分析了加工流畅性的影响机制.此外,虚假真实效应非常稳健,虽然一些方法能有效降低虚假真实效应,但仍没有办法完全消除.未来应该更多地从干预的角度出发探究如何有效地避免此效应对人们的影响.

The efficient Siamese anchor-free tracker has fewer parameters, but it produces a large number of low-quality bounding boxes which are located far away from the center of the object. Moreover, a plenty of background information or distractors also interfere with the tracking process, resulting in the inaccurate results of classification and regression. As such, we propose a novel Siamese anchor-free network based on criss-cross attention and an improved head network. We apply ResNet-50 to extract the features of the template image and search region, then feed the feature maps into a recurrent criss-cross attention module to make it more discriminative. The enhanced feature maps are inputted into our improved head network, which include the center-ness branch based on the original classification and regression branches to filter out low-quality bounding boxes. Our proposed tracker reduces the impact of background information or distractors and can obtain high-quality bounding boxes, generating more accurate and robust tracking results. Extensive experiments and comparisons with state-of-the-art trackers are conducted on many challenging benchmarks such as VOT2016, VOT2018, GOT-10k, UAV123 and OTB2015. Our tracker achieves excellent performance with a considerable real-time speed.

Background: Childhood emotional neglect (CEN) confers a great risk for developing multiple psychiatric disorders; however, the neural basis for this association remains unknown. Using a dynamic functional connectivity approach, this study aimed to examine the effects of CEN experience on functional brain networks in young adults.Method: In total, 21 healthy young adults with CEN experience and 26 without childhood trauma experience were recruited. The childhood trauma experience was assessed using the childhood trauma questionnaire (CTQ), and eligible participants underwent resting-state functional MRI. Sliding windows and k-means clustering were used to identify temporal features of large-scale functional connectivity states (frequency, mean dwell time, and transition numbers).Result: Dynamic analysis revealed two separate connection states: state 1 was more frequent and characterized by extensive weak connections between the brain regions. State 2 was relatively infrequent and characterized by extensive strong connections between the brain regions. Compared to the control group, the CEN group had a longer mean dwell time in state 1 and significantly decreased transition numbers between states 1 and 2.Conclusion: The CEN experience affects the temporal properties of young adults' functional brain connectivity. Young adults with CEN experience tend to be stable in state 1 (extensive weak connections between the brain regions), reducing transitions between states, and reflecting impaired metastability or functional network flexibility.

Objective:To investigate the characteristics of emotional face perception in college students with non-suicidal self-injury（NSSI） behavior.Methods:NSSI behavior was determined with the Ottawa Self-injury Inventory（at least once in a month） and Adolescents Self-Harm Scale（at least once in half a year）.Finally, 23 college students with NSSI behavior（NSSI group）and 24 students without NSSI（control group） were recruited.A mixed experimental design of 2（group: NSSI group, control group） × 4（emotional faces: angry, happy, neutral, surprised） was used to explore the differences in the accuracy and reaction time between the two groups when judging the face valence（positive or negative facial expression）.Results:Compared with the control group, the NSSI group judged the valence of emotional faces faster[（757±43）ms vs.（959±41）ms, P＜0.01],while there was no significant difference in accuracy between the two groups（P＞0.05）.In both groups, the response time to judge the valence of happy expression was the shortest, while the response time to judge the valence of surprised expression was the longest（P＜0.001）.Conclusion:It suggest that college students with non-suicidal self-injury behavior are more sensitive to emotional face valences.

Childhood emotional neglect (CEN) has a relatively high incidence rate and substantially adverse effects. Many studies have found that CEN is closely related to emotion regulation and depression symptoms. Besides, the functional activity of the prefrontal lobe may also be related to them. However, the relationships between the above variables have not been thoroughly studied. This study recruited two groups of college students, namely, those with primary CEN (neglect group) and those without childhood trauma (control group), to explore the relationships among CEN, adulthood emotion regulation, depressive symptoms, and prefrontal resting functional connections. The methods used in this study included the Childhood Trauma Questionnaire (CTQ), Emotion Regulation Questionnaire (ERQ), Beck Depression Inventory-II (BDI-II) and resting-state functional magnetic resonance imaging (rs-fMRI). The results showed that compared with the control group, the neglect group utilized the reappraisal strategy less frequently and displayed more depressive symptoms. The prefrontal functional connections with other brain regions in the neglect group were more robust than those in the control group using less stringent multiple correction standards. Across the two groups, the functional connection strength between the right orbitofrontal gyrus and the right middle frontal gyrus significantly negatively correlated with the ERQ reappraisal score and positively correlated with the BDI-II total score; the ERQ reappraisal score wholly mediated the relationship between the functional connection strength and the BDI-II total score. It suggests that primary CEN may closely correlate with more depressive symptoms in adulthood. Furthermore, the more robust spontaneous activity of the prefrontal lobe may also be closely associated with more depressive symptoms by utilizing a reappraisal strategy less frequently.

Compressive light field cameras have attracted notable attention over the past few years because they can efficiently determine redundancy from light fields. However, much of the research has only concentrated on reconstructing the entire light field from compressed sampling, which ignores the possibility of directly extracting information such as depth from it. In this paper, we introduce a light field camera configuration with a random color-coded microlens array. Considering the color-coded light fields, we propose a novel attention-based encoder–decoder network. Specifically, the encoder part compresses the coded measurement into a low-dimensional representation that removes most redundancy, and the decoder part constructs the depth map directly from the latent representation. The attention mechanism enables the network to process spatial and angular features dynamically and effectively, thus significantly improving performance. Extensive experiments on synthetic and real-world datasets show that our method outperforms the state-of-the-art light field depth estimation method designed for non-coded light fields. To our knowledge, this is the first study that combines the color-coded light field with the attention-based deep learning approach, which provides a crucial insight into the design of enhanced light field photography systems.

Childhood emotional neglect (CEN) refers to a failure to meet the basic emotional needs of a child, which can seriously impact interpersonal communication and psychological health in young adults. Emotional face processing is critical in interpersonal communication; however, whether CEN affects this processing in young adults has not been investigated. Therefore, the current study aimed to explore the effects of CEN on emotional face processing in young adults. Using the Child Trauma Questionnaire, an online survey was conducted with 5010 students from four universities in Tianjin, China. After online interviews and diagnosis by professional doctors, we obtained 20 participants with CEN (CEN group) and 20 without CEN (control group). None of the participants had any mental diseases. A 2 × 4 mixed design was used to investigate the differences in accuracy and response time when identifying the valence of the emotional faces. Compared to the control group, the CEN group identified the valence of all emotional faces more slowly, but there was no significant difference between the two groups in terms of accuracy. CEN caused delayed emotional face processing in young adults, which may be related to unresponsive, unavailable, and limited emotional interaction patterns between parents and their children.

以伴有单发性童年期情感忽视(CEN)和无任何童年期创伤经历的大学生为对象,借助问卷和静息态功能磁共振技术考察单发性CEN对大学生情绪调节能力及丘脑静息态功能连接的影响.结果发现,忽视组情绪调节更困难且更少使用重评策略,丘脑和背外侧额上回的功能连接更强;跨组分析中重评得分完全中介丘脑功能连接对情绪调节困难的影响.结果提示,单发性CEN可能诱发成人期的情绪调节困难,而丘脑自发活动的改变可能通过影响重评策略而影响其成人期情绪调节能力.

Traffic sign detection, as an important part of intelligent driving, can effectively guide drivers to regulate driving and reduce the occurrence of traffic accidents. Currently, the deep learning-based detection methods have achieved very good performance. However, existing network models do not adequately consider the importance of lower-layer features for traffic sign detection. The lack of information on the lower-layer features is a major obstacle to the accurate detection of traffic signs. To solve the above problems, we propose a novel and efficient traffic sign detection method. First, we remove a prediction branch of the YOLOv3 network model to reduce the redundancy of the network model parameters and improve the real-time performance of detection. After that, we propose a multiscale attention feature module. This module fuses the feature information from different layers and refines the features to enhance the Feature Pyramid Network. In addition, we introduce a spatial information aggregator. This enables the spatial information of the lower-layer feature maps to be fused into the higher-layer feature maps. The robustness of our proposed method is further demonstrated by experiments on GTSDB, CCTSDB2021 and TT100k datasets. Specifically, the average execution time on CCTSDB2021 demonstrates the excellent real-time performance of our method. The experimental results show that the method has better accuracy than the original YOLOv3 and YOLOv5 network models.

针对计算机类专业课程教学中培养大学生计算思维的困难现状,分析计算思维与问题解决能力之间的关系,提出一种聚焦计算思维培养的问题驱动教学模式,并以操作系统课程的"进程同步"为例,介绍创设情境、转换问题、构建模型、优化方案、提炼思维和应用拓展6个步骤的教学过程,最后通过数据分析和结果反馈,说明教学模式对计算思维培养的效果.

Robust and accurate visual tracking is a challenging problem in computer vision. In this paper, we exploit spatial and semantic convolutional features extracted from convolutional neural networks in continuous object tracking. The spatial features retain higher resolution for precise localization and semantic features capture more semantic information and less fine-grained spatial details. Therefore, we localize the target by fusing these different features, which improves the tracking accuracy. Besides, we construct the multi-scale pyramid correlation filter of the target and extract its spatial features. This filter determines the scale level effectively and tackles target scale estimation. Finally, we further present a novel model updating strategy, and exploit peak sidelobe ratio (PSR) and skewness to measure the comprehensive fluctuation of response map for efficient tracking performance. Each contribution above is validated on 50 image sequences of tracking benchmark OTB-2013. The experimental comparison shows that our algorithm performs favorably against 12 state-of-the-art trackers.

Regulatory focus theory uses two different motivation focus systems—promotional and preventive—to describe how individuals approach positive goals and avoid negative goals. Moreover, the regulatory focus can manifest as chronic personality characteristics and can be situationally induced by tasks or the environment. The current study employed eye-tracking methodology to investigate how individuals who differ in their chronic regulatory focus (promotional vs. preventive) process information (Experiment 1) and whether an induced experimental situation could modulate features of their information processing (Experiment 2). Both experiments used a 3 × 3 grid information-processing task, containing eight information cells and a fixation cell; half the information cells were characterized by attribute-based information, and the other half by alternative-based information. We asked the subjects to view the grid based on their personal preferences and choose one of the virtual products presented in this grid to “purchase” by the end of each trial. Results of Experiment 1 show that promotional individuals do not exhibit a clear preference between the two types of information, whereas preventive individuals tend to fixate longer on the alternative-based information. In Experiment 2, we induced the situational regulatory focus via experimental tasks before the information-processing task. The results demonstrate that the behavioral motivation is significantly enhanced, thereby increasing the depth of the preferred mode of information processing, when the chronic regulatory focus matches the situational focus. In contrast, individuals process information more thoroughly, using both processing modes, in the non-fit condition, i.e., when the focuses do not match.

Over these years, object tracking algorithms combined with correlation filters and convolutional features have achieved excellent performance in accuracy and real-time speed. However, tracking failures in some challenging sequences are caused by the insensitivity of deeper convolutional features to target appearance changes and the unreasonable updating of correlation filters. In this paper, we propose dual model learning combined with multiple feature selection for accurate visual tracking. First, we fuse the handcrafted features with the multi-layer features extracted from the convolutional neural network to construct a correlation filter learning model, which can precisely localize the target. Second, we propose an index named hierarchical peak to sidelobe ratio (HPSR). The fluctuation of HPSR determines the activation of an online classifier learning model to redetect the target. Finally, the target locations predicted by the dual learning models mentioned above are combined to obtain the final target position. With the help of dual learning models, the accuracy and performance of tracking have been greatly improved. The results on the OTB-2013 and OTB-2015 datasets show that the proposed algorithm achieves the highest success rate and precision compared with the 12 state-of-the-art tracking algorithms. The proposed method is better adaptive to various challenges in visual object tracking.

Object tracking is easily influenced by illumination, occlusion, scale, background clutter, and fast motion, and it requires higher real-time performance. The object tracking algorithm based on compressive sensing has a better real-time performance but performs weakly in tracking when object appearance is changed greatly. Based on the framework of compressive sensing, a Multi-Model real-time Compressive Tracking (MMCT) algorithm is proposed, which adopts the compressive sensing to decrease the high dimensional features for the tracking process and to satisfy the real-time performance. The MMCT algorithm selects the most suitable classifier by judging the maximum classification score difference of classifiers in the previous two frames, and enhances the accuracy of location. The MMCT algorithm also presents a new model update strategy, which employs the fixed or dynamic learning rates according to the differences of decision classifiers and improves the precision of classification. The multi-model introduced by MMCT does not increase the computational burden and shows an excellent real-time performance. The experimental results indicate that the MMCT algorithm can well adapt to illumination, occlusion, background clutter and plane-rotation.

In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn't need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFacel, which uses pairs of face images as inputs and maps them to target space so that the L2 norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.

Object tracking is a vital topic in computer vision. Although tracking algorithms have gained great development in recent years, its robustness and accuracy still need to be improved. In this paper, to overcome single feature with poor representation ability in a complex image sequence, we put forward a multifeature integration framework, including the gray features, Histogram of Gradient (HOG), color-naming (CN), and Illumination Invariant Features (IIF), which effectively improve the robustness of object tracking. In addition, we propose a model updating strategy and introduce a skewness to measure the confidence degree of tracking result. Unlike previous tracking algorithms, we judge the relationship of skewness values between two adjacent frames to decide the updating of target appearance model to use a dynamic learning rate. This way makes our tracker further improve the robustness of tracking and effectively prevents the target drifting caused by occlusion and deformation. Extensive experiments on large-scale benchmark containing 50 image sequences show that our tracker is better than most existing excellent trackers in tracking performance and can run at average speed over 43 fps.