Local Context Features Research Articles

How Context Matters: The Significance of Political Homogeneity and Language for Political Efficacy

The extent of political efficacy within a community reflects the general state of affairs within that community, with higher levels of political efficacy presumably related to other kinds of socially preferable attitudes. High levels of political efficacy could further be regarded as a glue that keeps a political community together and should be even more important within minority communities. As political efficacy differs across minority communities, it indicates that individual levels of political efficacy is not only an individual trait but something also affected by the local contextual features. To explore the relationship between varying local contexts and political efficacy within a minority population, we use data from Barometern 2019 (N = 3,913), which is a survey measuring the opinions and attitudes of the Swedish‐speaking population in Finland, i.e., the Swedish‐speaking Finns. This study, thus, analyses the role of contextual‐ and individual‐level determinants (e.g., age, education and gender) as well as linguistic identity (Swedish and bilingual) and political interest on both internal (subjective sense of political understanding) and external (political responsiveness) political efficacy. We find that context matters for political efficacy within a minority context but that the effects differ between the internal and external types of political efficacy. The findings presented will contribute to increasing our knowledge about political efficacy within a minority context.

News Text Classification Method and Simulation Based on the Hybrid Deep Learning Model

This paper uses the database as the data source, using bibliometrics and visual analysis methods, to statistically analyze the relevant documents published in the field of text classification in the past ten years, to clarify the development context and research status of the text classification field, and to predict the research in the field of text classification priorities and research frontiers. Based on the in-depth study of the background, research status, related theories, and developments of online news text classification, this article analyzes the annual publication trend, subject distribution, journal distribution, institution distribution, author distribution, highly cited literature analysis, and research hotspots. Forefront and other aspects clarify the development context and research status of the text classification field and provide a theoretical reference for the further development of the text classification field. Then, on the basis of systematic research on text classification, deep learning, and news text classification theories, a deep learning-based network news text classification model is constructed, and the function of each module is introduced in detail, which will help the future news text classification of application and improvement provide theoretical basis. On the basis of the predecessors, this article separately studied and improved the neural network model based on the convolutional neural network, cyclic neural network, and attention mechanism and merged the three models into one model, which can obtain local associated features and contextual features and highlight the role of keywords. Finally, experiments are used to verify the effectiveness of the model proposed in this paper and compared with traditional text classification to prove the superiority of the network news text classification based on deep learning proposed in this paper. This article aims to study the internal connection between news comments and the number of votes received by news comments, and through the proposed model, the number of votes for news comments can be predicted.

Attention Capsule Network for Aspect-Level Sentiment Classification

As a fine-grained classification problem, aspect-level sentiment classification predicts the sentiment polarity for different aspects in context. To address this issue, researchers have widely used attention mechanisms to abstract the relationship between context and aspects. Still, it is difficult to effectively obtain a more profound semantic representation, and the strong correlation between local context features and the aspect-based sentiment is rarely considered. In this paper, a hybrid attention capsule network for aspect-level sentiment classification (ABASCap) was proposed. In this model, the multi-head self-attention was improved, and a context mask mechanism based on adjustable context window was proposed, so as to effectively obtain the internal association between aspects and context. Moreover, the dynamic routing algorithm and activation function in capsule network were optimized to meet the task requirements. Finally, sufficient experiments were conducted on three benchmark datasets in different domains. Compared with other baseline models, ABASCap achieved better classification results, and outperformed the state-of-the-art methods in this task after incorporating pre-training BERT.

KVGCN: A KNN Searching and VLAD Combined Graph Convolutional Network for Point Cloud Segmentation

Semantic segmentation of the sensed point cloud data plays a significant role in scene understanding and reconstruction, robot navigation, etc. This work presents a Graph Convolutional Network integrating K-Nearest Neighbor searching (KNN) and Vector of Locally Aggregated Descriptors (VLAD). KNN searching is utilized to construct the topological graph of each point and its neighbors. Then, we perform convolution on the edges of constructed graph to extract representative local features by multiple Multilayer Perceptions (MLPs). Afterwards, a trainable VLAD layer, NetVLAD, is embedded in the feature encoder to aggregate the local and global contextual features. The designed feature encoder is repeated for multiple times, and the extracted features are concatenated in a jump-connection style to strengthen the distinctiveness of features and thereby improve the segmentation. Experimental results on two datasets show that the proposed work settles the shortcoming of insufficient local feature extraction and promotes the accuracy (mIoU 60.9% and oAcc 87.4% for S3DIS) of semantic segmentation comparing to existing models.

SalED: Saliency prediction with a pithy encoder-decoder architecture sensing local and global information

This paper proposes a deep convolutional neural network with a concise and effective encoder-decoder architecture for saliency prediction. Local and global contextual features make a considerable contribution to saliency prediction. In order to integrate and exploit these features more thoroughly, in the proposed pithy architecture, we deploy a dense and global context connection structure between the encoder and decoder, after that, a multi-scale readout module is designed to process various information from the previous portion of the decoder with different parallel mapping relationships for full-scale accurate results. Our model ranks first in light of multiple metrics on two famous saliency benchmarks and performs good generalization on other datasets. Besides, we evaluate the precision and the speed of our model with different backbones. The saliency prediction performance of VGGNet-Based, ResNet-based, and DenseNet-based model gradually increases while the speed also drops off. And the experiments illustrate that our model performs better than other models even if replacing the backbone of our model with the same backbone of the compared model. Therefore, we can provide optional versions of our model for different requirements of performance and efficiency.

Comprehensive Study on Enhancing Low-Quality Position-Specific Scoring Matrix with Deep Learning for Accurate Protein Structure Property Prediction: Using Bagging Multiple Sequence Alignment Learning.

Accurate predictions of protein structure properties, for example, secondary structure and solvent accessibility, are essential in analyzing the structure and function of a protein. Position-specific scoring matrix (PSSM) features are widely used in the structure property prediction. However, some proteins may have low-quality PSSM features due to insufficient homologous sequences, leading to limited prediction accuracy. To address this limitation, we propose an enhancing scheme for PSSM features. We introduce the "Bagging MSA" (multiple sequence alignment) method to calculate PSSM features used to train our model, adopt a convolutional network to capture local context features and bidirectional long short-term memory for long-term dependencies, and integrate them under an unsupervised framework. Structure property prediction models are then built upon such enhanced PSSM features for more accurate predictions. Moreover, we develop two frameworks to evaluate the effectiveness of the enhanced PSSM features, which also bring proposed method into real-world scenarios. Empirical evaluation of CB513, CASP11, and CASP12 data sets indicates that our unsupervised enhancing scheme indeed generates more informative PSSM features for structure property prediction.

Towards accurate RGB-D saliency detection with complementary attention and adaptive integration

Saliency detection based on the complementary information from RGB images and depth maps has recently gained great popularity. In this paper, we propose Complementary Attention and Adaptive Integration Network (CAAI-Net), a novel RGB-D saliency detection model that integrates complementary attention based feature concentration and adaptive cross-modal feature fusion into a unified framework for accurate saliency detection. Specifically, we propose a context-aware complementary attention (CCA) module, which consists of a feature interaction component, a complementary attention component, and a global-context component. The CCA module first utilizes the feature interaction component to extract rich local context features. The resulting features are then fed into the complementary attention component, which employs the complementary attention generated from adjacent levels to guide the attention at the current layer so that the mutual background disturbances are suppressed and the network focuses more on the areas with salient objects. Finally, we utilize a specially-designed adaptive feature integration (AFI) module, which sufficiently considers the low-quality issue of depth maps, to aggregate the RGB and depth features in an adaptive manner. Extensive experiments on six challenging benchmark datasets demonstrate that CAAI-Net is an effective saliency detection model and outperforms nine state-of-the-art models in terms of four widely-used metrics. In addition, extensive ablation studies confirm the effectiveness of the proposed CCA and AFI modules.

D-Net: A Generalised and Optimised Deep Network for Monocular Depth Estimation

Depth estimation is an essential component in computer vision systems for achieving 3D scene understanding. Efficient and accurate depth map estimation has numerous applications including self-driving vehicles and virtual reality tools. This paper presents a new deep network, called D-Net, for depth estimation from a single RGB image. The proposed network can be trained end-to-end, and its structure can be customised to meet different requirements in model size, speed, and prediction accuracy. Our approach gathers strong global and local contextual features at multiple resolutions, and then transfers these to high resolutions for clearer depth maps. For the encoder backbone, D-Net can utilise many state-of-the-art models including EfficientNet, HRNet and Swin Transformer to obtain dense depth maps. The proposed D-net is designed to have minimal parameters and reduced computational complexity. Extensive evaluations on the NYUv2 and KITTI benchmark datasets show that our model is highly accurate across multiple backbones, and it achieves state-of-the-art performance on both benchmarks when combined with the Swin Transformer and HRNets.

The Centerline Extraction Algorithm of Weld Line Structured Light Stripe Based on Pyramid Scene Parsing Network

Based on the good feature learning ability of the pyramid scene parsing network, a method for extracting the centerline of structured light stripes of weld lines based on the pyramid scene parsing network and Steger algorithm is proposed. This method avoids the traditional complex weld image preprocessing technology, and simplifies the operation steps of extracting the centerline of the structured light stripe of the weld image line. In this paper, the pyramid scene parsing network is used to predict the pixels containing weld feature information. Through the pyramid pooling module, the local and global context feature information is fused to supplement the feature information of the weld edge, and then the Steger algorithm is used to extract the weld feature centerline. The results show that the method in this paper can accurately extract the centerline position of the structured light stripe of the weld line under the interference of reflection, and the average value reaches 86.8% on the accuracy evaluation index mean intersection over union, the 18.93 pixels on the weld extraction accuracy index root mean square error, and the average time of extracting the center line of structured light stripe of weld line is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.188s$ </tex-math></inline-formula> .

DLLNet: An Attention-Based Deep Learning Method for Dental Landmark Localization on High-Resolution 3D Digital Dental Models.

Dental landmark localization is a fundamental step to analyzing dental models in the planning of orthodontic or orthognathic surgery. However, current clinical practices require clinicians to manually digitize more than 60 landmarks on 3D dental models. Automatic methods to detect landmarks can release clinicians from the tedious labor of manual annotation and improve localization accuracy. Most existing landmark detection methods fail to capture local geometric contexts, causing large errors and misdetections. We propose an end-to-end learning framework to automatically localize 68 landmarks on high-resolution dental surfaces. Our network hierarchically extracts multi-scale local contextual features along two paths: a landmark localization path and a landmark area-of-interest segmentation path. Higher-level features are learned by combining local-to-global features from the two paths by feature fusion to predict the landmark heatmap and the landmark area segmentation map. An attention mechanism is then applied to the two maps to refine the landmark position. We evaluated our framework on a real-patient dataset consisting of 77 high-resolution dental surfaces. Our approach achieves an average localization error of 0.42 mm, significantly outperforming related start-of-the-art methods.

CDD-Net: A Context-Driven Detection Network for Multiclass Object Detection

Unlike object detection in natural images that usually achieved great success, remote sensing imagery has its own challenges to detect and localize multiclass objects, such as large-scale change, uncertain direction, and high density. The context information of the objects is very worthwhile for solving these challenges in remote sensing images. In this letter, we propose a context-driven detection network (CDD-Net) to improve the accuracy of multiclass object detection in remote sensing images. For capturing the local neighboring objects and features, a local context feature network (LCFN) is proposed to learn the local context of the region of interest. Meanwhile, a hybrid attention pyramid network (HAPN) is designed, which can steer the focus to more valuable features. The HAPN inserts a squeeze and excitation block (SEB) and three asymmetric convolution blocks (ACBs) in the feature pyramid network (FPN). The experimental results over the DOTA-v1.5 data set demonstrate that the proposed CDD-Net yields promising results.

Chinese agricultural diseases and pests named entity recognition with multi-scale local context features and self-attention mechanism

Chinese named entity recognition is a crucial initial step of information extraction in the field of agricultural diseases and pests. This step aims to identify named entities related to agricultural diseases and pests from unstructured texts but presents challenges. The available corpus in this domain is limited, and most existing named entity recognition methods only focus on the global context information but neglect potential local context features, which are also equally important for named entity recognition. To solve the above problems and tackle the named entity recognition task in this paper, an available corpus toward agricultural diseases and pests, namely AgCNER, which contains 11 categories and 34,952 samples, was established. Compared with the corpora in the same field, this corpus has additional categories and more sample sizes. Then, a novel Chinese named entity recognition model via joint multi-scale local context features and the self-attention mechanism was proposed. The original Bi-directional Long Short-Term Memory and Conditional Random Field model (BiLSTM-CRF) was improved by fusing the multi-scale local context features extracted by Convolutional Neural Network (CNN) with different kernel sizes. The self-attention mechanism was also used to break the limitation of BiLSTM-CRF in capturing long-distance dependencies and further improve the model performance. The performance of the proposed model was evaluated on three corpora, namely AgCNER, Resume, and MSRA, which achieved the optimal F1-values of 94.15%, 94.56%, and 90.55%, respectively. Experimental results in many aspects illustrated the effective performance of the proposed model in this paper.

AMD-GAN: Attention encoder and multi-branch structure based generative adversarial networks for fundus disease detection from scanning laser ophthalmoscopy images

The scanning laser ophthalmoscopy (SLO) has become an important tool for the determination of peripheral retinal pathology, in recent years. However, the collected SLO images are easily interfered by the eyelash and frame of the devices, which heavily affect the key feature extraction of the images. To address this, we propose a generative adversarial network called AMD-GAN based on the attention encoder (AE) and multi-branch (MB) structure for fundus disease detection from SLO images. Specifically, the designed generator consists of two parts: the AE and generation flow network, where the real SLO images are encoded by the AE module to extract features and the generation flow network to handle the random Gaussian noise by a series of residual block with up-sampling (RU) operations to generate fake images with the same size as the real ones, where the AE is also used to mine features for generator. For discriminator, a ResNet network using MB is devised by copying the stage 3 and stage 4 structures of the ResNet-34 model to extract deep features. Furthermore, the depth-wise asymmetric dilated convolution is leveraged to extract local high-level contextual features and accelerate the training process. Besides, the last layer of discriminator is modified to build the classifier to detect the diseased and normal SLO images. In addition, the prior knowledge of experts is utilized to improve the detection results. Experimental results on the two local SLO datasets demonstrate that our proposed method is promising in detecting the diseased and normal SLO images with the experts labeling.

Deep Kernel Density Estimation for Photon Mapping

AbstractRecently, deep learning‐based denoising approaches have led to dramatic improvements in low sample‐count Monte Carlo rendering. These approaches are aimed at path tracing, which is not ideal for simulating challenging light transport effects like caustics, where photon mapping is the method of choice. However, photon mapping requires very large numbers of traced photons to achieve high‐quality reconstructions. In this paper, we develop the first deep learning‐based method for particle‐based rendering, and specifically focus on photon density estimation, the core of all particle‐based methods. We train a novel deep neural network to predict a kernel function to aggregate photon contributions at shading points. Our network encodes individual photons into per‐photon features, aggregates them in the neighborhood of a shading point to construct a photon local context vector, and infers a kernel function from the per‐photon and photon local context features. This network is easy to incorporate in many previous photon mapping methods (by simply swapping the kernel density estimator) and can produce high‐quality reconstructions of complex global illumination effects like caustics with an order of magnitude fewer photons compared to previous photon mapping methods. Our approach largely reduces the required number of photons, significantly advancing the computational efficiency in photon mapping.

An Improved Topology Prediction of Alpha-Helical Transmembrane Protein Based on Deep Multi-Scale Convolutional Neural Network.

Alpha-helical proteins ( αTMPs) are essential in various biological processes. Despite their tertiary structures are crucial for revealing complex functions, experimental structure determination remains challenging and costly. In the past decades, various sequence-based topology prediction methods have been developed to bridge the gap between the sequences and structures by characterizing the structural features, but significant improvements are still required. Deep learning brings a great opportunity for its powerful representation learning capability from limited original data. In this work, we improved our αTMP topology prediction method DMCTOP using deep learning, which composed of two deep convolutional blocks to simultaneously extract local and global contextual features. Consequently, the inputs were simplified to reflect the original features of the sequence, including a protein sequence feature and an evolutionary conservation feature. DMCTOP can efficiently and accurately identify all topological types and the N-terminal orientation for an αTMP sequence. To validate the effectiveness of our method, we benchmarked DMCTOP against 13 peer methods according to the whole sequence, the transmembrane segment and the traditional criterion in testing experiments. All the results reveal that our method achieved the highest prediction accuracy and outperformed all the previous methods. The method is available at https://icdtools.nenu.edu.cn/dmctop.

Attentive convolutional gated recurrent network: a contextual model to sentiment analysis

Considering contextual features is a key issue in sentiment analysis. Existing approaches including convolutional neural networks (CNNs) and recurrent neural networks (RNNs) lack the ability to account and prioritize informative contextual features that are necessary for better sentiment interpretation. CNNs present limited capability since they are required to be very deep, which can lead to the gradient vanishing whereas, RNNs fail because they sequentially process input sequences. Furthermore, the two approaches treat all words equally. In this paper, we suggest a novel approach named attentive convolutional gated recurrent network (ACGRN) that alleviates the above issues for sentiment analysis. The motivation behind ACGRN is to avoid the vanishing gradient caused by deep CNN via applying a shallow-and-wide CNN that learns local contextual features. Afterwards, to solve the problem caused by the sequential structure of RNN and prioritizing informative contextual information, we use a novel prior knowledge attention based bidirectional gated recurrent unit (ATBiGRU). Prior knowledge ATBiGRU captures global contextual features with a strong focus on the previous hidden states that carry more valuable information to the current time step. The experimental results show that ACGRN significantly outperforms the baseline models over six small and large real-world datasets for the sentiment classification task.

Deep Multi-Scale Mesh Feature Learning for Automated Labeling of Raw Dental Surfaces From 3D Intraoral Scanners.

Precisely labeling teeth on digitalized 3D dental surface models is the precondition for tooth position rearrangements in orthodontic treatment planning. However, it is a challenging task primarily due to the abnormal and varying appearance of patients' teeth. The emerging utilization of intraoral scanners (IOSs) in clinics further increases the difficulty in automated tooth labeling, as the raw surfaces acquired by IOS are typically low-quality at gingival and deep intraoral regions. In recent years, some pioneering end-to-end methods (e.g., PointNet) have been proposed in the communities of computer vision and graphics to consume directly raw surface for 3D shape segmentation. Although these methods are potentially applicable to our task, most of them fail to capture fine-grained local geometric context that is critical to the identification of small teeth with varying shapes and appearances. In this paper, we propose an end-to-end deep-learning method, called MeshSegNet, for automated tooth labeling on raw dental surfaces. Using multiple raw surface attributes as inputs, MeshSegNet integrates a series of graph-constrained learning modules along its forward path to hierarchically extract multi-scale local contextual features. Then, a dense fusion strategy is applied to combine local-to-global geometric features for the learning of higher-level features for mesh cell annotation. The predictions produced by our MeshSegNet are further post-processed by a graph-cut refinement step for final segmentation. We evaluated MeshSegNet using a real-patient dataset consisting of raw maxillary surfaces acquired by 3D IOS. Experimental results, performed 5-fold cross-validation, demonstrate that MeshSegNet significantly outperforms state-of-the-art deep learning methods for 3D shape segmentation.

Deep Learning Model for Fine-Grained Aspect-Based Opinion Mining

Despite the great manufactures’ efforts to achieve customer satisfaction and improve their performance, social media opinion mining is still on the fly a big challenge. Current opinion mining requires sophisticated feature engineering and syntactic word embedding without considering semantic interaction between aspect term and opinionated features, which degrade the performance of most of opinion mining tasks, especially those that are designed for smart manufacturing. Research on intelligent aspect level opinion mining (AOM) follows the fast proliferation of user-generated data through social media for industrial manufacturing purposes. Google’s pre-trained language model, Bidirectional Encoder Representations from Transformers (BERT) widely overcomes existing methods in eleven natural language processing (NLP) tasks, which makes it the standard way for semantic text representation. In this paper, we introduce a novel deep learning model for fine-grained aspect-based opinion mining, named as FGAOM. First, we train the BERT model on three specific domain corpora for domain adaption, then use adjusted BERT as embedding layer for concurrent extraction of local and global context features. Then, we propose Multi-head Self-Attention (MSHA) to effectively fuse internal semantic text representation and take advantage of convolutional layers to model aspect term interaction with surrounding sentiment features. Finally, the performance of the proposed model is evaluated via extensive experiments on three public datasets. Results show that performance of the proposed model outperforms performances of recent the-of-the-art models.

PaDNet: Pan-Density Crowd Counting.

Crowd counting is a highly challenging problem in computer vision and machine learning. Most previous methods have focused on consistent density crowds, i.e., either a sparse or a dense crowd, meaning they performed well in global estimation while neglecting local accuracy. To make crowd counting more useful in the real world, we propose a new perspective, named pan-density crowd counting, which aims to count people in varying density crowds. Specifically, we propose the Pan-Density Network (PaDNet) which is composed of the following critical components. First, the Density-Aware Network (DAN) contains multiple subnetworks pretrained on scenarios with different densities. This module is capable of capturing pandensity information. Second, the Feature Enhancement Layer (FEL) effectively captures the global and local contextual features and generates a weight for each density-specific feature. Third, the Feature Fusion Network (FFN) embeds spatial context and fuses these density-specific features. Further, the metrics Patch MAE (PMAE) and Patch RMSE (PRMSE) are proposed to better evaluate the performance on the global and local estimations. Extensive experiments on four crowd counting benchmark datasets, the ShanghaiTech, the UCF-CC-50, the UCSD, and the UCFQNRF, indicate that PaDNet achieves state-of-the-art recognition performance and high robustness in pan-density crowd counting.

Superpixel-Based Conditional Random Fields (SuperCRF): Incorporating Global and Local Context for Enhanced Deep Learning in Melanoma Histopathology.

Computational pathology-based cell classification algorithms are revolutionizing the study of the tumor microenvironment and can provide novel predictive/prognosis biomarkers crucial for the delivery of precision oncology. Current algorithms used on hematoxylin and eosin slides are based on individual cell nuclei morphology with limited local context features. Here, we propose a novel multi-resolution hierarchical framework (SuperCRF) inspired by the way pathologists perceive regional tissue architecture to improve cell classification and demonstrate its clinical applications. We develop SuperCRF by training a state-of-art deep learning spatially constrained- convolution neural network (SC-CNN) to detect and classify cells from 105 high-resolution (20×) H&E-stained slides of The Cancer Genome Atlas melanoma dataset and subsequently, a conditional random field (CRF) by combining cellular neighborhood with tumor regional classification from lower resolution images (5, 1.25×) given by a superpixel-based machine learning framework. SuperCRF led to an 11.85% overall improvement in the accuracy of the state-of-art deep learning SC-CNN cell classifier. Consistent with a stroma-mediated immune suppressive microenvironment, SuperCRF demonstrated that (i) a high ratio of lymphocytes to all lymphocytes within the stromal compartment (p = 0.026) and (ii) a high ratio of stromal cells to all cells (p < 0.0001 compared to p = 0.039 for SC-CNN only) are associated with poor survival in patients with melanoma. SuperCRF improves cell classification by introducing global and local context-based information and can be implemented in combination with any single-cell classifier. SuperCRF provides valuable tools to study the tumor microenvironment and identify predictors of survival and response to therapy.