EXPRESS: The Influence of Three-Dimensional Cues on Body Size Judgements

Research has shown that body size judgements are frequently biased, or inaccurate. Critically, judgement biases are further exaggerated for individuals with eating disorders, a finding that has been attributed to difficulties integrating body features into a perceptual whole. However, current understanding of which body features are integrated when judging body size is lacking. In this study, we examine whether individuals integrate three-dimensional (3D) cues to body volume when making body size judgements. Computer-generated body stimuli were presented in a 3D Virtual Reality (VR) environment. Participants (N = 412) were randomly assigned to one of two conditions: in one condition the to-be-judged body was displayed binocularly (containing 3D cues to body volume), in the other, bodies were presented monocularly (2D cues only). Across 150 trials, participants were required to make a body size judgement of a target female body from a third-person point of view using an unmarked visual analogue scale (VAS). It was found that 3D cues significantly influenced body size judgements. Namely, thin 3D bodies were judged smaller, and overweight 3D bodies were judged larger, than their 2D counterpart. Furthermore, to reconcile these effects, we present evidence that the two perceptual biases, regression to the mean and serial dependence, were reduced by the additional 3D feature information. Our findings increase our understanding of how body size is perceptually encoded and creates testable predictions for clinical populations exhibiting integration difficulties.

Forest Fire Detection via Feature Entropy Guided Neural Network

Forest fire detection from videos or images is vital to forest firefighting. Most deep learning based approaches rely on converging image loss, which ignores the content from different fire scenes. In fact, complex content of images always has higher entropy. From this perspective, we propose a novel feature entropy guided neural network for forest fire detection, which is used to balance the content complexity of different training samples. Specifically, a larger weight is given to the feature of the sample with a high entropy source when calculating the classification loss. In addition, we also propose a color attention neural network, which mainly consists of several repeated multiple-blocks of color-attention modules (MCM). Each MCM module can extract the color feature information of fire adequately. The experimental results show that the performance of our proposed method outperforms the state-of-the-art methods.

Single-Stage Adaptive Multi-Scale Point Cloud Noise Filtering Algorithm Based on Feature Information

This paper proposes a single-stage adaptive multi-scale noise filtering algorithm for point clouds, based on feature information, which aims to mitigate the fact that the current laser point cloud noise filtering algorithm has difficulty quickly completing the single-stage adaptive filtering of multi-scale noise. The feature information from each point of the point cloud is obtained based on the efficient k-dimensional (k-d) tree data structure and amended normal vector estimation methods, and the adaptive threshold is used to divide the point cloud into large-scale noise, a feature-rich region, and a flat region to reduce the computational time. The large-scale noise is removed directly, the feature-rich and flat regions are filtered via improved bilateral filtering algorithm and weighted average filtering algorithm based on grey relational analysis, respectively. Simulation results show that the proposed algorithm performs better than the state-of-art comparison algorithms. It was, thus, verified that the algorithm proposed in this paper can quickly and adaptively (i) filter out large-scale noise, (ii) smooth small-scale noise, and (iii) effectively maintain the geometric features of the point cloud. The developed algorithm provides research thought for filtering pre-processing methods applicable in 3D measurements, remote sensing, and target recognition based on point clouds.

Mid-level feature differences underlie early animacy and object size distinctions: Evidence from EEG decoding

Responses to visually-presented objects along the cortical surface of the human brain have a large-scale organization reflecting the broad categorical divisions of animacy and object size. Mounting evidence indicates that this topographical organization is driven by differences between objects in mid-level perceptual features. With regard to the timing of neural responses, images of objects quickly evoke neural responses with decodable information about animacy and object size, but are mid-level features sufficient to evoke these rapid neural responses? Or is slower iterative neural processing required to untangle information about animacy and object size from mid-level features? To answer this question, we used electroencephalography(EEG) to measure human neural responses to images of objects and their texform counterparts - unrecognizable images which preserve some mid-level feature information about texture and coarse form. We found that texform images evoked neural responses with early decodable information about both animacy and real-world size, as early as responses evoked by original images. Further, successful cross-decoding indicates that both texform and original images evoke information about animacy and size through a common underlying neural basis. Broadly, these results indicate that the visual system contains a mid-level feature bank carrying linearly decodable information on animacy and size, which can be rapidly activated without requiring explicit recognition or protracted temporal processing.

FCAU-Net for the Semantic Segmentation of Fine-Resolution Remotely Sensed Images

The semantic segmentation of fine-resolution remotely sensed images is an urgent issue in satellite image processing. Solving this problem can help overcome various obstacles in urban planning, land cover classification, and environmental protection, paving the way for scene-level landscape pattern analysis and decision making. Encoder-decoder structures based on attention mechanisms have been frequently used for fine-resolution image segmentation. In this paper, we incorporate a coordinate attention (CA) mechanism, adopt an asymmetric convolution block (ACB), and design a refinement fusion block (RFB), forming a network named the fusion coordinate and asymmetry-based U-Net (FCAU-Net). Furthermore, we propose novel convolutional neural network (CNN) architecture to fully capture long-term dependencies and fine-grained details in fine-resolution remotely sensed imagery. This approach has the following advantages: (1) the CA mechanism embeds position information into a channel attention mechanism to enhance the feature representations produced by the network while effectively capturing position information and channel relationships; (2) the ACB enhances the feature representation ability of the standard convolution layer and captures and refines the feature information in each layer of the encoder; and (3) the RFB effectively integrates low-level spatial information and high-level abstract features to eliminate background noise when extracting feature information, reduces the fitting residuals of the fused features, and improves the ability of the network to capture information flows. Extensive experiments conducted on two public datasets (ZY-3 and DeepGlobe) demonstrate the effectiveness of the FCAU-Net. The proposed FCAU-Net transcends U-Net, Attention U-Net, the pyramid scene parsing network (PSPNet), DeepLab v3+, the multistage attention residual U-Net (MAResU-Net), MACU-Net, and the Transformer U-Net (TransUNet). Specifically, the FCAU-Net achieves a 97.97% (95.05%) pixel accuracy (PA), a 98.53% (91.27%) mean PA (mPA), a 95.17% (85.54%) mean intersection over union (mIoU), and a 96.07% (90.74%) frequency-weighted IoU (FWIoU) on the ZY-3 (DeepGlobe) dataset.

Multipath Cross Graph Convolution for Knowledge Representation Learning

In the past, most of the entity prediction methods based on embedding lacked the training of local core relationships, resulting in a deficiency in the end-to-end training. Aiming at this problem, we propose an end-to-end knowledge graph embedding representation method. It involves local graph convolution and global cross learning in this paper, which is called the TransC graph convolutional network (TransC-GCN). Firstly, multiple local semantic spaces are divided according to the largest neighbor. Secondly, a translation model is used to map the local entities and relationships into a cross vector, which serves as the input of GCN. Thirdly, through training and learning of local semantic relations, the best entities and strongest relations are found. The optimal entity relation combination ranking is obtained by evaluating the posterior loss function based on the mutual information entropy. Experiments show that this paper can obtain local entity feature information more accurately through the convolution operation of the lightweight convolutional neural network. Also, the maximum pooling operation helps to grasp the strong signal on the local feature, thereby avoiding the globally redundant feature. Compared with the mainstream triad prediction baseline model, the proposed algorithm can effectively reduce the computational complexity while achieving strong robustness. It also increases the inference accuracy of entities and relations by 8.1% and 4.4%, respectively. In short, this new method can not only effectively extract the local nodes and relationship features of the knowledge graph but also satisfy the requirements of multilayer penetration and relationship derivation of a knowledge graph.

Prediction of Alzheimer’s Disease Based on Coordinate-Dense Attention Network

Alzheimer’s disease (AD) is a degenerative disease of the nervous system. Mild cognitive impairment (MCI) is a condition between brain aging and dementia. The prediction will be divided into stable sMCI and progressive pMCI as a binary task. Structural magnetic resonance imaging (sMRI) can describe structural changes in the brain and provide a diagnostic method for the detection and early prevention of Alzheimer’s disease. In this paper, an automatic disease prediction scheme based on MRI was designed. A dense convolutional network was used as the basic model. By adding a channel attention mechanism to the model, significant feature information in MRI images was extracted, and the unimportant features were ignored or suppressed. The proposed framework is compared with the most advanced methods, and better results are obtained.

CSFF-Net: Scene Text Detection Based on Cross-Scale Feature Fusion

In the last years, methods for detecting text in real scenes have made significant progress with an increase in neural networks. However, due to the limitation of the receptive field of the central nervous system and the simple representation of text by using rectangular bounding boxes, the previous methods may be insufficient for working with more challenging instances of text. To solve this problem, this paper proposes a scene text detection network based on cross-scale feature fusion (CSFF-Net). The framework is based on the lightweight backbone network Resnet, and the feature learning is enhanced by embedding the depth weighted convolution module (DWCM) while retaining the original feature information extracted by CNN. At the same time, the 3D-Attention module is also introduced to merge the context information of adjacent areas, so as to refine the features in each spatial size. In addition, because the Feature Pyramid Network (FPN) cannot completely solve the interdependence problem by simple element-wise addition to process cross-layer information flow, this paper introduces a Cross-Level Feature Fusion Module (CLFFM) based on FPN, which is called Cross-Level Feature Pyramid Network (Cross-Level FPN). The proposed CLFFM can better handle cross-layer information flow and output detailed feature information, thus improving the accuracy of text region detection. Compared to the original network framework, the framework provides a more advanced performance in detecting text images of complex scenes, and extensive experiments on three challenging datasets validate the realizability of our approach.

Multi-Level Fusion Temporal–Spatial Co-Attention for Video-Based Person Re-Identification

A convolutional neural network can easily fall into local minima for insufficient data, and the needed training is unstable. Many current methods are used to solve these problems by adding pedestrian attributes, pedestrian postures, and other auxiliary information, but they require additional collection, which is time-consuming and laborious. Every video sequence frame has a different degree of similarity. In this paper, multi-level fusion temporal–spatial co-attention is adopted to improve person re-identification (reID). For a small dataset, the improved network can better prevent over-fitting and reduce the dataset limit. Specifically, the concept of knowledge evolution is introduced into video-based person re-identification to improve the backbone residual neural network (ResNet). The global branch, local branch, and attention branch are used in parallel for feature extraction. Three high-level features are embedded in the metric learning network to improve the network’s generalization ability and the accuracy of video-based person re-identification. Simulation experiments are implemented on small datasets PRID2011 and iLIDS-VID, and the improved network can better prevent over-fitting. Experiments are also implemented on MARS and DukeMTMC-VideoReID, and the proposed method can be used to extract more feature information and improve the network’s generalization ability. The results show that our method achieves better performance. The model achieves 90.15% Rank1 and 81.91% mAP on MARS.