A model of impulsive octonion-valued fuzzy inertial neural networks (OVFINNs) with time-varying delays is established, and fixed-time (FXT) synchronization is investigated by using direct octonion approach. First, a new FXT stability lemma of impulsive systems is presented and the upper bound of settling time is estimated by using the average impulsive interval and comparison principle. Second, two inequalities on fuzzy logic are developed in the field of octonion. Third, novel lemmas are introduced based on octonion-valued norm and sign function to overcome the non associative and non commutative laws of octonion multiplication. Furthermore, two new nonlinear octonion-valued controllers are directly designed to induce the FXT synchronization. Then, according to the improving FXT stability lemma and designed controllers, some novel sufficient conditions are given to ensure FXT synchronization of OVFINNs. Finally, two numerical simulations are given to demonstrate the correctness of the theoretical results and the effectiveness of FXT synchronization in secure communication.

Insomnia is the most common sleep disorder linked with adverse long-term medical and psychiatric outcomes. Automatic sleep staging plays a crucial role in aiding doctors to diagnose insomnia disorder. Only a few studies have been conducted to develop automatic sleep staging methods for insomniacs, and most of them have utilized transfer learning methods, which involve pre-training models on healthy individuals and then fine-tuning them on insomniacs. Unfortunately, significant differences in feature distribution between the two subject groups impede the transfer performance, highlighting the need to effectively integrate the features of healthy subjects and insomniacs. In this paper, we propose a dual-teacher cross-domain knowledge transfer method based on the feature-based knowledge distillation to improve the performance of sleep staging for insomniacs. Specifically, the insomnia teacher directly learns from insomniacs and feeds the corresponding domain-specific features into the student network, while the health domain teacher guide the student network to learn domain-generic features. During the training process, we adopt the OFD (Overhaul of Feature Distillation) method to build the health domain teacher. We conducted the experiments to validate the proposed method, using the Sleep-EDF database as the source domain and the CAP-Database as the target domain. The results demonstrate that our method surpasses advanced techniques, achieving an average sleep staging accuracy of 80.56% on the CAP-Database. Furthermore, our method exhibits promising performance on the private dataset.

Few-shot learning aims to recognize novel categories solely relying on a few labeled samples, with existing few-shot methods primarily focusing on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured, and the actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we investigate an interesting and challenging cross-domain few-shot learning task, where the training and testing tasks employ different domains. Specifically, we propose a Meta-Memory scheme to bridge the domain gap between source and target domains, leveraging style-memory and content-memory components. The former stores intra-domain style information from source domain instances and provides a richer feature distribution. The latter stores semantic information through exploration of knowledge of different categories. Under the contrastive learning strategy, our model effectively alleviates the cross-domain problem in few-shot learning. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on cross-domain few-shot semantic segmentation tasks on the COCO-20$^{i}$, PASCAL-5$^{i}$, FSS-1000, and SUIM datasets and positively affects few-shot classification tasks on Meta-Dataset.

Recommender systems based on graph attention networks have received increasing attention due to their excellent ability to learn various side information. However, previous work usually focused on game character recommendation without paying much attention to items. In addition, as the team of the match changes, the items used by the characters may also change. To overcome these limitations, we propose a relation-aware graph attention item recommendation method. It considers the relationship between characters and items. Furthermore, the graph attention mechanism aggregates the embeddings of items and analyzes the effects of items on related characters while assigning attention weights between characters and items. Extensive experiments on the kaggle public game dataset show that our method significantly outperforms previous methods in terms of Precision, F1 and MAP compared to other existing methods.

Few-shot semantic segmentation intends to predict pixel-level categories using only a few labeled samples. Existing few-shot methods focus primarily on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured. The actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we propose an interesting and challenging cross-domain few-shot semantic segmentation task, where the training and test tasks perform on different domains. Specifically, we first propose a meta-memory bank to improve the generalization of the segmentation network by bridging the domain gap between source and target domains. The meta-memory stores the intra-domain style information from source domain instances and transfers it to target samples. Subsequently, we adopt a new contrastive learning strategy to explore the knowledge of different categories during the training stage. The negative and positive pairs are obtained from the proposed memory-based style augmentation. Comprehensive experiments demon-strate that our proposed method achieves promising results on cross-domain few-shot semantic segmentation tasks on COCO-20i, PASCAL-Si, FSS-1000, and SUIM datasets.

Recently, convolutional neural networks (CNNs) have demonstrated impressive capabilities in the representation and classification of hyperspectral remote sensing images. Traditional CNNs require massive data to sufficiently train the network. To tackle this problem, graph convolutional network (GCN) has been introduced for hyperspectral image classification. GCN methods usually construct the graph from either spectral or spatial domain, which has not adequately explored the information in the joint spectral–spatial domain. In this article, we propose a superpixel spectral–spatial feature fusion graph convolution network for hyperspectral image classification (S3FGCN). S3FGCN can comprehensively use information in spectral, spatial, and spectral–spatial domains with limited data. Moreover, to enhance the performance, we explore a shared weights’ GCN in the spectral–spatial domain. To further improve the efficiency, superpixels are used to construct the adjacency matrix. Finally, dynamic sampling is adopted to make the model focus more on difficult samples. In the experiments on four datasets, S3FGCN demonstrates better accuracy compared with the state-of-the-art hyperspectral image classification methods.

Electroencephalography (EEG) is a commonly used clinical approach for the diagnosis of epilepsy which is a life-threatening neurological disorder. Many algorithms have been proposed for the automatic detection of epileptic seizures using traditional machine learning and deep learning. Although deep learning methods have achieved great success in many fields, their performance in EEG analysis and classification is still limited mainly due to the relatively small sizes of available datasets. In this paper, we propose an automatic method for the detection of epileptic seizures based on deep metric learning which is a novel strategy tackling the few-shot problem by mitigating the demand for massive data. First, two one-dimensional convolutional embedding modules are proposed as a deep feature extractor, for single-channel and multichannel EEG signals respectively. Then, a deep metric learning model is detailed along with a stage-wise training strategy. Experiments are conducted on the publicly-available Bonn University dataset which is a benchmark dataset, and the CHB-MIT dataset which is larger and more realistic. Impressive averaged accuracy of 98.60% and specificity of 100% are achieved on the most difficult classification of interictal (subset D) vs ictal (subset E) of the Bonn dataset. On the CHB-MIT dataset, an averaged accuracy of 86.68% and specificity of 93.71% are reached. With the proposed method, automatic and accurate detection of seizures can be performed in real time, and the heavy burden of neurologists can be effectively reduced.

Pavement crack detection is of great significance for road maintenance. However, the complexity of road surfaces and the irregularity of cracks make it difficult to accurately detect crack regions. We propose a crack detection method based on structural features for the patch-wise crack detection. The novelty of this method lies on the fusion of the local patches in a multi-staged strategy. Deep supervision learning is further used to learn these features at each stage. The fusion features model the structural relevance among cracks. The experimental results prove the effectiveness of our method on the dataset collected from the industrial environments. Among these state-of-the-art methods we compared, our model achieved the best experimental results with an AP 86.97%.

Summary Epilepsy seriously damages the physical and mental health of patients. Detection of epileptic EEG signals in different periods can help doctors diagnose the disease. The change of frequency components during epilepsy seizures is obvious, and there may be noises in epilepsy EEG signals. Moreover, epileptic seizures are closely related to the release of neuronal spiking in the brain. In this paper, we propose an approach for epilepsy period classification based on combination feature extraction methods and spiking swarm intelligent optimization classification algorithm. First, combination feature extraction methods take in account both the time‐frequency features and principal component features of epilepsy. The time‐frequency features are obtained by WPT or STFT‐PSD, and noises are removed while extracting principal component features by PCA. Second, spiking swarm intelligent optimization classification algorithm takes advantage of individual cooperation and information interaction with strong robustness. Its simulated neurons are closer to reality, which consider more information and obtain stronger computing power. The experimental results show that the average classification accuracy of the proposed method can reach 98.95% and the highest classification accuracy can reach 100%. Compared with other methods, the proposed method has the best classification performance.

Weakly supervised video object segmentation (WSVOS) is a vital yet challenging task in which the aim is to segment pixel-level masks with only category labels. Existing methods still have certain limitations, e.g., difficulty in comprehending appropriate spatiotemporal knowledge and an inability to explore common semantic information with category labels. To overcome these challenges, we formulate a novel framework by integrating multisource saliency and incorporating an exemplar mechanism for WSVOS. Specifically, we propose a multisource saliency module to comprehend spatiotemporal knowledge by integrating spatial and temporal saliency as bottom-up cues, which can effectively eliminate disruptions due to confusing regions and identify attractive regions. Moreover, to our knowledge, we make the first attempt to incorporate an exemplar mechanism into WSVOS by proposing an adaptive exemplar module to process top-down cues, which can provide reliable guidance for co-occurring objects in intraclass videos and identify attentive regions. Our framework, which comprises the two aforementioned modules, offers a new perspective on directly constructing the correspondence between bottom-up cues and top-down cues when ground-truth information for the reference frames is lacking. Comprehensive experiments demonstrate that the proposed framework achieves state-of-the-art performance.

Nuclei segmentation plays an important role in cancer diagnosis. Automated methods for digital pathology become popular due to the developments of deep learning and neural networks. However, this task still faces challenges. Most of current techniques cannot be applied directly because of the clustered state and the large number of nuclei in images. Moreover, anchor-based methods for object detection lead a huge amount of calculation, which is even worse on pathological images with a large target density. To address these issues, we propose a novel network with an anchor-free detection and a U-shaped segmentation. An altered feature enhancement module is attached to improve the performance in dense target detection. Meanwhile, the U-Shaped structure in segmentation block ensures the aggregation of features in different dimensions generated from the backbone network. We evaluate our work on a Multi-Organ Nuclei Segmentation dataset from MICCAI 2018 challenge. In comparisons with others, our proposed method achieves state-of-the-art performance.

In machine learning and data mining applications, clustering is a critical task for knowledge discovery that attract attentions from large quantities of researchers. Generally, with the help of label information, supervised learning methods have more flexible structure and better result than unsupervised learning. However, supervised learning is infeasible for clustering task. In this paper, to fill the gap between clustering and supervised learning, the proposed clustering methods introduce the exemplars discriminative information into a supervised learning. To build the effective objective function, a strategy for reducing intracluster distance and increasing intercluster distance is introduced to form a unified optimization objective function. With initially setting the clustering centers, the data that near the centers are selected as exemplars to indicate the ground truth of different classes. Discriminative learning is then introduced to learn the partition hyperplane and classify all the data into different classes. New clustering centers are calculated for selecting new exemplars alternately. Using the proposed algorithms, the unsupervised K -means clustering problem is effectively solved from the perceptive of optimization. Feature mapping is also introduced to improve the performance by reducing the intercluster distance. A novel framework for exploring discriminative information from unsupervised data is provided. The proposed algorithms outperform the state-of-the-art approaches on a wide range of benchmark datasets in terms of accuracy.

Crack width is an important indicator to diagnose the safety of constructions, e.g., asphalt road, concrete bridge. In practice, measuring crack width is a challenge task: (1) the irregular and non-smooth boundary makes the traditional method inefficient; (2) pixel-wise measurement guarantees the accuracy of a system and (3) understanding the damage of constructions from any pre-selected points is a mandatary requirement. To address these problems, we propose a cascade Principal Component Analysis (PCA) to efficiently measure crack width from images. Firstly, the binary crack image is obtained to describe the crack via the off-the-shelf crack detection algorithms. Secondly, given a pre-selected point, PCA is used to find the main axis of a crack. Thirdly, Robust Principal Component Analysis (RPCA) is proposed to compute the main axis of a crack with a irregular boundary. We evaluate the proposed method on a real data set. The experimental results show that the proposed method achieves the state-of-the-art performances in terms of efficiency and effectiveness.

Convolutional Neural Networks (CNNs) have delivered impressive state-of-the-art performances for many vision tasks, while the computation costs of these networks during test-time are notorious. Empirical results have discovered that CNNs have learned the redundant representations both within and across different layers. When CNNs are applied for binary classification, we investigate a method to exploit this redundancy across layers, and construct a cascade of classifiers which explicitly balances classification accuracy and hierarchical feature extraction costs. Our method cost-sensitively selects feature points across several layers from trained networks and embeds non-expensive yet discriminative features into a cascade. Experiments on binary classification demonstrate that our framework leads to drastic test-time improvements, e.g., possible 47.2x speedup for TRECVID upper body detection, 2.82x speedup for Pascal VOC2007 People detection, 3.72x for INRIA Person detection with less than 0.5% drop in accuracies of the original networks.

Due to the diversity of body movements and uncertainty of recording occasion, human action recognition is still a challenging task, especially in real world. This paper provides a new method of representing the video with mid-level vision representation which is extracted from the discriminative supervoxels. In the proposed method, the discriminative supervoxels we extracted through a learning phase frequently occur within class and are distinguishing enough between classes. They contain the meaningful parts of the video, including specific background of an action and the moving human body. The video is first oversegmented to obtain supervoxels, which are described by the dense trajectories and Bag-Of-Words framework. Afterwards, the discriminative supervoxels are extracted by an iterative procedure through training and selecting. Finally the videos are represented with discriminative supervoxels. Experimental results on KTH, YouTube and UT-Interaction datasets demonstrate comparable performance with state-of-the-art models.

Abstract In the paper, we present an interactive image‐segmentation method in the framework of graph cut, which incorporates not only traditional color and gradient constraints, but also a new type of texture constraint. Given an image with user‐input strokes, we first establish the color and texture prior models of the foreground/background. The texture prior model, which is key to establish the texture constraints, is represented by local binary patterns (LBP) histograms. Then, an energy function composed of color, gradient, and texture terms is formulated. At last, by using graph cut, we minimize the energy function to obtain the foreground. In the energy function, the color and gradient terms have similar forms with traditional methods. The texture term in the function is generated using a proposed randomized texton‐searching algorithm. First, the algorithm locates an approximately best representative texton for every unknown pixel as foreground and an approximately best one as background, through randomized searching. Second, it computes the LBP histograms of the two textons as the pixel's foreground/background texture descriptors, respectively. Finally, the distances between the descriptors and the foreground/background prior models are used to formulate the texture term. Experimental results demonstrate that our method outperforms traditional ones. Copyright © 2015 John Wiley & Sons, Ltd.

Target searching, i.e. fast locating target objects in images or videos, has attracted much attention in computer vision. A comprehensive understanding of factors influencing human visual searching is essential to design target searching algorithms for computer vision systems. In this paper, we propose a combined model to generate scan paths for computer vision to follow to search targets in images. The model explores and integrates three factors influencing human vision searching, top-down target information, spatial context and bottom-up visual saliency, respectively. The effectiveness of the combined model is evaluated by comparing the generated scan paths with human vision fixation sequences to locate targets in the same images. The evaluation strategy is also used to learn the optimal weighting coefficients of the factors through linear search. In the meanwhile, the performances of every single one of the factors and their arbitrary combinations are examined. Through plenty of experiments, we prove that the top-down target information is the most important factor influencing the accuracy of target searching. The effects from the bottom-up visual saliency are limited. Any combinations of the three factors have better performances than each single component factor. The scan paths obtained by the proposed model are optimal, since they are most similar to the human vision fixation sequences.

In this paper, a new visual saliency detection method is proposed based on the spatially weighted dissimilarity. We measured the saliency by integrating three elements as follows: the dissimilarities between image patches, which were evaluated in the reduced dimensional space, the spatial distance between image patches and the central bias. The dissimilarities were inversely weighted based on the corresponding spatial distance. A weighting mechanism, indicating a bias for human fixations to the center of the image, was employed. The principal component analysis (PCA) was the dimension reducing method used in our system. We extracted the principal components (PCs) by sampling the patches from the current image. Our method was compared with four saliency detection approaches using three image datasets. Experimental results show that our method outperforms current state-of-the-art methods on predicting human fixations.

This paper presents an improved neural architecture for gaze movement control in target searching. Compared with the four-layer neural structure proposed in [14], a new movement coding neuron layer is inserted between the third layer and the fourth layer in previous structure for finer gaze motion estimation and control. The disadvantage of the previous structure is that all the large responding neurons in the third layer were involved in gaze motion synthesis by transmitting weighted responses to the movement control neurons in the fourth layer. However, these large responding neurons may produce different groups of movement estimation. To discriminate and group these neurons' movement estimation in terms of grouped connection weights form them to the movement control neurons in the fourth layer is necessary. Adding a new neuron layer between the third layer and the fourth lay is the measure that we solve this problem. Comparing experiments on target locating showed that the new architecture made the significant improvement.

We propose an image conspicuity index that combines three factors: spatial dissimilarity, spatial distance and central bias. The dissimilarity between image patches is evaluated in a reduced dimensional principal component space and is inversely weighted by the spatial separations between patches. An additional weighting mechanism is deployed that reflects the bias of human fixations towards the image center. The method is tested on three public image datasets and a video clip to evaluate its performance. The experimental results indicate highly competitive performance despite the simple definition of the proposed index. The conspicuity maps generated are more consistent with human fixations than prior state-of-the-art models when tested on color image datasets. This is demonstrated using both receiver operator characteristics (ROC) analysis and the Kullback-Leibler distance metric. The method should prove useful for such diverse image processing tasks as quality assessment, segmentation, search, or compression. The high performance and relative simplicity of the conspicuity index relative to other much more complex models suggests that it may find wide usage.

Gaze movement plays an important role in human visual search system. In literature, the winner-take-all method is wildly used to simulate the controlling of the gaze movement. The winner-take-all is a type of single-cell coding method, which uses one cell (grandmother cell) or one response to represent an object. However, eye movement is affected by the visual context which includes more than one object in images, especially in target search. Therefore, we propose to use the population coding with more than one response rather than the single-cell coding on gaze movement control. The proposed method is supported by the theoretical analysis and experiments on a real image database which show the population-cell-coding improves the target locating accuracy by 44.4% only at the cost of coding 22.4% more information than that of single-cell-coding.

Visual context between objects is an important cue for object position perception. How to effectively represent the visual context is a key issue to study. Some past work introduced task-driven methods for object perception, which led a large coding quantity. This paper proposes an approach that incorporates feature-driven mechanism into object-driven context representation for object locating. As an example, the paper discusses how a neuronal network encodes the visual context between feature salient regions and human eye centers with as little coding quantity as possible. A group of experiments on efficiency of visual context coding and object searching are analyzed and discussed, which show that the proposed method decreases the coding quantity and improve the object searching accuracy effectively.

Pulse-coupled neuron networks (PCNN) can be efficiently applied to image segmentation. However, the performance of segmentation depends on the suitable PCNN parameters, which are obtained by manual experiment, and the effect of the segmentation needs to be improved for images with noise. In this paper, dynamic mechanism based PCNN(DMPCNN) is brought forward to simulate the integrate-and-fire mechanism, and it is applied to segment images with noise effectively. Parameter selection is based on dynamic mechanism. Experimental results for image segmentation show its validity and robustness.

To deal with security challenges in context-aware model, we propose a pervasive computing terminal equipment architecture in which trusted computing technology is introduced. First, we give out a context- aware processing model for pervasive computing. Second, security requirements and challenges on terminal contextual processing are analyzed. To solve these security challenges, we apply trusted measure, trusted I/O, trusted storage and trusted report to achieve authenticity, confidentiality, privacy and integrity. Compared with traditional methods, the terminal architecture embedded with trust provides a better solution in dynamic and open pervasive computing environment.

Research on efficiency of learning and memory is very important for theoretic exploration and practical application. This paper gives a discussion on learning and memory of spatial relationships between initial positions and object positions by a neural network with sparse features. As an example, the paper discusses how the neural network learns the visual contexts between human eye centers and random initial positions surrounding the eye centers in images with as little memory as possible. Some sparse features are designed and distances between initial positions and the labeled eye centers in horizontal and vertical directions are learned and memorized respectively. Such a system could predict object positions from a new initial position according to the contexts that the neural network learned. A group of experiments on efficiency of learning and memory with sparse features in several single and integrated scales are analyzed and discussed.

A semantic model - IISM (image internal semantic model) is introduced. Unlike other semantic extracting methods, IISM extracts the semantic information not by image segmentation and image understanding, but by analyzing relevance feedback image retrieval results. For relevance feedback image retrieval system, the images relevant to query are pointed as positive example, otherwise the images irrelevant to query are pointed as negative examples. It is assumed that these positive examples are related in semantic content. IISM computes comprehensive pair-wise mutual information for all images through analyzing the results of relevance feedback image retrieval. An association with a high mutual information means that one image is semantically associated with another. Semantic retrieval and clustering is carried out based on these association relationships.