Image classification has become highly significant in the field of computer vision due to its wide array of applications. In recent years, Convolutional Neural Networks (CNN) have emerged as potent tools for addressing this task. Attention mechanisms offer an effective approach to enhance the accuracy of image classification. Despite Global Average Pooling (GAP) being a crucial component of traditional attention mechanisms, it only computes the average of spatial elements in each channel, failing to capture the complete range of feature information, resulting in fewer and less expressive features. To address this limitation, we propose a novel pooling operation named “Binary Pooling” and integrate it into the attention block. Binary pooling combines both GAP and Global Max Pooling (GMP), obtaining a more comprehensive feature vector by extracting average and maximum values, thereby enriching the diversity of extracted image features. Furthermore, to further enhance the extraction of image features, dilation operations and pointwise convolutions are applied on the channel-wise. The proposed attention block is simple yet highly effective. Upon integration into ResNet18/50 models, it leads to accuracy improvements of 2.02%/0.63% on ImageNet.

Searching for neighbors for a query node in a spatial network is a fundamental problem and has been extensively investigated. However, most existing works focus only on the node level when conducting such a query and rarely pay attention to the social relations among the neighbors. We argue that a user, in some cases, is more likely to engage in some activities collectively, i.e., going to the bar with friends rather than alone. For this reason, we consider the neighbor searching problem at a community level in this paper and examine a new problem: Neighboring Geosocial Communities Search (NGCS) over large spatial graphs. Specifically, given a parameter $n$ and query node $q$ , we aim to find the top- $n$ nearest communities for $q$ . Moreover, in each returned community, nodes have cohesive relations with each other and are covered by a minimum covering circle (MCC) whose radius is less than $r$ . It is obvious that the NGCS problem finds its standard applications in marketing and other scenarios but it is very challenging for large spatial graphs because it requires detecting all qualified cohesive user communities. Therefore, in this paper, we adopt a local search approach to reduce the difficulty. The introduced algorithm finds the top- $n$ neighboring geo-social communities through a progressive search in the graph without thoroughly examining the graph. Analyses show that the complexity of the algorithm is decreased by an order of magnitude. Extensive experiments on real social networks confirm the superiority and effectiveness of our solutions.

Biological control often combines selective sensing, complementary response scales, and attenuation under weak evidence. Guided by these principles, this paper presents Spectrum-Guided Identifiable Single-Anchor Range Compensation (SGIS-RC), a deterministic physics–data framework for single-anchor scalar-range compensation. SGIS-RC removes the local anchor–bias nuisance tangent from the kinematic sensitivity, retains a numerically conditioned physical subspace, and models the remaining discrepancy through a Chebyshev–Matérn global–local residual field. The learned correction is further regulated by leverage, configuration-space support, and bounded amplitude control. On two public workbooks, ABB IRB120 and HSR-C JR680, a pre-specified outer-partition evaluation performed after the model specification was frozen yielded configuration-group MAEs of $0.2306\pm 0.0148$ mm and $0.0493\pm 0.0021$ mm, respectively, while the matched conventional hybrid yielded slightly lower mean errors of $0.2244\pm 0.0151$ mm and $0.0478\pm 0.0015$ mm. Same-fit analyses show that support placement can alter the balance between global and local residual correction, and the block protocols indicate that support-shift behavior remains dataset dependent. Overall, SGIS-RC provides a structured and auditable framework that integrates identifiability-aware physical adaptation, global–local residual modeling, and support-aware deployment control for single-anchor scalar-range compensation.