ABSTRACT Aspect‐Based Sentiment Triplet Extraction (ASTE) is one of the hot topics in recent years. Relevant researchers have proposed many neural network models for aspect‐based sentiment triplet extraction. However, they fail to model the complex syntactic and semantic associations between tokens, which limits the synergy of features from different angles, which may lead to inaccurate encoding of the relationship between tokens and thus inaccurate extraction of triples. In response to the problems mentioned above, a graph attention aggregation network with multi‐level Syntactic and Semantic Enhanced Prompts for aspect‐Based sentiment triple extraction (SSEP) is proposed. First, a graph attention relation aggregation module is designed in the context encoding part. Specifically, the module first constructs a relation aggregation graph through the output of the pre‐trained language model, then designs a graph attention aggregator, and finally aggregates the multi‐level output of the pre‐trained language model according to the relation aggregation graph and the graph attention aggregator. Second, a syntactic and semantic enhanced prompt module is proposed. The module uses relation table attention to prompt the model, and then uses a dual‐channel graph neural network to further enhance syntactic and semantic information and prune unimportant information. In addition, a joint boundary detection module is designed. The module can directly extract sentiment triplets using joint boundary detection labels. Finally, experimental results on four public datasets show that SSEP achieves state‐of‐the‐art performance and outperforms other models.

Recent weakly supervised image dehazing (WSID) works have succeeded to improve models’ generalization ability to real scene dehazing by using generative adversarial network (GAN) for unpaired image training. However, it is still difficult for current WSID methods to train one effective dehazing model for various scenes since 1) they always result in residual haze due to insufficient generalization to the feature distribution of real scenes, and 2) they are prone to cause distortions like color shifts, artifacts or halos etc, owing to embedding manual prior or threshold hypothesis for image reconstruction. To solve above problems, in this paper, we propose a novel WSID model via physics-based decomposition (PBD), which estimates atmospheric light, scattering coefficient and scene depth of real haze input to effectively capture the illumination information and haze distribution to recover a preliminary dehazed image by minimizing reconstruction loss. With this constraint, we subtly design a discrete wavelet discriminator (DWD) to effectively improve the generalization to real scene from both spatial and frequency aspect under the supervision of unpaired real clear image. Our PBD is a purely data-driven model freeing from any manual setting or partially correct prior, thus simultaneously ensuring the realness and visibility of dehazed images. Experiments on seven benchmarks verified the strong generalization ability of our PBD, which achieves SOTA dehazing performance with realistic details. Code will be published at https://github.com/NianWang-HJJGCDX/PBD.

Image dehazing is essential to boost the visual quality of images captured in hazy conditions. Recently, many learning-based methods were proposed to achieve single image dehazing with the training of tremendous paired synthetic hazy/ real clean images. Due to the domain gap between real and synthetic scenes, these models cannot generalize well to various real hazy scenes, leading to under-dehazed results. To overcome this problem, we propose a real scene image Dehazing Network with Multi-prior Guidance and Domain Transfer (DNMGDT). Our DNMGDT is based on a parameter shared architecture trained by synthetic hazy images and real hazy images simultaneously. For real hazy images, multiple prior-based dehazed images are adopted as pseudo clean images. An Image Quality Guided Adaptive Weighting (IQGAW) scheme is proposed to form the supervision by automatically weighting different parts of these prior-based dehazed images and suppressing negative information of them. Moreover, to reduce the domain gap between real and synthetic hazy scenes, a Physical Model Guided image level Domain Transfer (PMGDT) mechanism is proposed to regularize the learning process with consistency constraint. Experiments on various datasets demonstrated the effectiveness of our proposed method especially for real hazy scenes.

Graph-based clustering is a hot topic in machine learning, whose effectiveness highly relies on the quality of the learned graph. Recent researches preferred to learn the nearest doubly stochastic approximation of a graph to suppress intercluster connections and enhance intracluster connections and thus improve clustering performance. While current paradigm is limited by three key problems: 1) it is restricted by a predefined graph; 2) the separated stages of spectral decomposition-based way (graph learning, spectral embedding learning, and cluster assignment by k-means) cause mismatched problems and randomness; and 3) the optimization of doubly stochastic conditions is generally achieved by von Neumann successive projection (VNSP) lemma, which separates the conditions to form two subproblems for alternative optimization, converging only to a feasible solution. To solve these problems, in this article, a novel structured doubly stochastic graph-based clustering model termed SDSGC is proposed, which learns a structured doubly stochastic graph from data to directly provide cluster indicators. For optimization, a simple but effective augmented Lagrangian multiplier (ALM)-based method is proposed, which optimizes all the doubly stochastic conditions simultaneously to obtain the optimal solution. Experiments on one toy dataset and eight ad hoc noised face datasets have demonstrated that the proposed SDSGC is more robust to noise. Furthermore, a quantitative comparison of ten benchmarks has verified our SDSGC achieves better clustering performance when compared with SOTA methods. The code is available at https://github.com/NianWang-HJJGCDX/SDSGC.git.

Abstract The elderly care station is a new concept, which is the terminal service institution of the home‐based elderly care system in Beijing. Because its supervision of service quality (SQ) is not standardized and its current subsidy is irrelevant to SQ, this paper provides a framework for an evaluation system of the elderly care station. An SQ evaluation index system for the elderly care station is designed according to the service and construction standards. A fuzzy hierarchical entropy method is then used to identify the weights such that the calculation steps are reduced and the decision‐making process is more objective. Based on that, a fuzzy comprehensive evaluation model is established. For integrating the SQ and service quantity provided by stations, a quality‐quantity quadrant model is proposed, which is used to discover the stations or operators with adequate SQ and service quantity to subsidy and the inadequate to give priority attention and rectification by quantifying and visualizing the service situation of all stations and their operators. Meanwhile, we conduct an empirical analysis by using the data of one station.

End-to-end learning-based image dehazing methods tend to overdehaze or underdehaze in real scenes due to inefficient feature extraction and feature fusion. In this letter, we propose a multiscale supervision-guided context aggregation network (MSGCAN) based on two principles: improving feature extraction and enhancing feature mapping. To improve feature extraction, an attention-guided context aggregation (AGCA) module is adopted to merge context features extracted by several residual dense blocks (RDB). Moreover, we output these aggregated context features on each scale and form multiscale supervision to enhance feature mapping and ensure that the extracted features on each scale contain more realistic details. The experimental results show that the proposed MSGCAN performs better than other state-of-the-art dehazing methods in both synthetic and real-world scenes.

Data-driven fault diagnosis primarily involves the identification of different fault locations and fault severities. Focusing on a challenging task for which the target fault severities do not exist in the training samples, this article proposes a generalized cross-severity bearing fault diagnosis scheme based on a novel hierarchical cross-category inference framework. The proposed method uses an outlier detection scheme based on unsupervised feature mapping and local outlier probability calculation to identify the unseen samples. A neural network embedded with a tree-structured decision layer acts as a backbone to execute fault diagnosis at different hierarchies for different sample types, seen or unseen. Additionally, the metric learning method is used to support the approximate severity inference of the unseen samples after the fault locations are identified in the hierarchical model. Experiments performed on an aeronautical bearing test rig revealed that the proposed scheme is both feasible and superior to existing methods.

This paper proposes a novel information hiding method designed for H.266/Versatile Video Coding (VVC) compressed video streams. In this work, we explore two exclusive tools in H.266/VVC standard, named Multiple Transform Selection (MTS) and Cross-component linear model (CCLM), to hide information. These two tools are utilized to preserve high video reconstruction quality and compression efficiency as well as enhance hidden capacity. In specific, MTS is for hiding information into luminance blocks by modifying the selections of transforms. Comparing with other tools, MTS has less significant impact on compression quality and efficiency. In addition, CCLM is further used to hide information into chrominance blocks to further enlarge the hidden capacity with little impact on the other two metrics. To our best knowledge, it is the first information hiding method exclusively designed for H.266/VVC. Experimental results show that our proposed information hiding method ensures high hidden capacity, remarkable video reconstruction quality and insignificant impact on compression efficiency, which achieves better overall performances comparing to existing methods for compressed video.

Abstract Single‐image dehazing is an important problem because it is a key prerequisite for most high‐level computer vision tasks. Traditional prior‐based methods adopt priors generated from clear images to restrain the atmospheric scattering model and then recover haze‐free images. However, these prior‐based methods always encounter over‐enhancement, such as halos and colour distortion. To solve this problem, many works use a convolutional neural network to retrieve original images. However, without priors as guidance, these learning‐based methods dehaze effectively in synthetic datasets but perform poorly in real scenes. Hence, in this paper, we propose a prior‐guided multiscale network for single‐image dehazing named PGMNet. Specifically, prior‐based methods are adopted to acquire dehazed images of the training dataset in advance and then send these dehazed images to a parameter‐shared encoder to form multiscale features. During the decoding process, these multiscale features are adopted to guide the prior‐guided multiscale network to recover more image details. Moreover, considering that these prior‐based dehazed images usually contain some over‐enhanced regions, a spatial attention guided feature aggregation module and squeeze‐and‐excitation module are adopted to alleviate colour distortion. The proposed PGMNet takes the advantage of prior‐based methods in real haze removal and provides superior performance compared with the state‐of‐the‐art methods on both synthetic and real‐world datasets.

Intelligent vehicles face considerable challenges in the complex traffic environment since they need to deal with various constraints and elements. This dissertation puts forward a novel trajectory planning framework for intelligent vehicles to generate safe and optimal driving trajectories. First, we design a spatiotemporal occupancy framework to deal with all kinds of elements in the complex driving environment based on the Frenét frame. This framework unifies various constraints on the road in the three-dimensional spatiotemporal representation and clearly describes the collision-free configuration space. Then we use the convex approximation method to construct a time-varying convex feasible region based on the above accurate temporal and spatial description. We formulate the trajectory planning problem as a standard quadratic programming formulation with collision-free and dynamics constraints. Finally, we apply the iterative convex optimization algorithm to solve the quadratic programming problem in the time-varying convex feasible region. Moreover, we design several typical experimental scenarios and have verified that the proposed method has good effectiveness and real-time.

With the explosion of social media networks, many modern applications are concerning about people's connections, which leads to the so-called social computing. An elusive question is to study how opinion communities form and evolve in real-world networks with great individual diversity and complex human connections. In this scenario, the classic K-means technique and its extended versions could not be directly applied, as they largely ignore the relationship among interactive objects. On the other side, traditional community detection approaches in statistical physics would be neither adequate nor fair: they only consider the network topological structure but ignore the heterogeneous-objects' attributive information. To this end, we attempt to model a realistic social media network as a discrete-time dynamical system, where the opinion matrix and the community structure could mutually affect each other. In this paper, community detection in social media networks is naturally formulated as a multi-objective optimization problem (MOOP), i.e., finding a set of densely connected components with similar opinion vectors. We propose a novel and powerful graph K-means framework, which is composed of three coupled phases in each discrete-time period. Specifically, the first phase uses a fast heuristic approach to identify those opinion leaders who have relatively high local reputation; the second phase adopts a novel dynamic game model to find the locally Pareto-optimal community structure; and the final phase employs a robust opinion dynamics model to simulate the evolution of the opinion matrix. We conduct a series of comprehensive experiments on real-world benchmark networks to validate the performance of GK-means through comparisons with the state-of-the-art graph clustering technologies.

Nonnegative matrix factorization (NMF) has been widely used in hyperspectral unmixing (HU). However, most NMF-based methods have single-layer structures, which may achieve poor performance for complex data. Deep learning, with its carefully designed hierarchical structure, has shown great advantages in learning data features. In this letter, we design a deep NMF structure by unfolding NMF into multilayers and present a sparsity-constrained deep NMF method for HU. In each layer, the abundance matrix is directly decomposed into the abundance matrix and endmember matrix of the next layer. Due to the nonconvexity of the NMF model, sparsity constraint is added to each layer using a L1regularizer of the abundance matrix on each layer. To get better initial parameters for the deep NMF network, a layer-wise pretraining strategy based on Nesterov's accelerated gradient algorithm is put forward to initialize the network. An alternative update method is also proposed to further fine-tune the network to get final decomposition results. The experimental results based on synthetic data and real data demonstrate that the proposed method outperforms several other state-of-the-art unmixing approaches.

Mining communities or clusters in networks is valuable in analyzing, designing, and optimizing many natural and engineering complex systems, e.g., protein networks, power grid, and transportation systems. Most of the existing techniques view the community mining problem as an optimization problem based on a given quality function(e.g., modularity), however none of them are grounded with a systematic theory to identify the central nodes in the network. Moreover, how to reconcile the mining efficiency and the community quality still remains an open problem. In this paper, we attempt to address the above challenges by introducing a novel algorithm. First, a kernel function with a tunable influence factor is proposed to measure the leadership of each node, those nodes with highest local leadership can be viewed as the candidate central nodes. Then, we use a discrete-time dynamical system to describe the dynamical assignment of community membership; and formulate the serval conditions to guarantee the convergence of each node's dynamic trajectory, by which the hierarchical community structure of the network can be revealed. The proposed dynamical system is independent of the quality function used, so could also be applied in other community mining models. Our algorithm is highly efficient: the computational complexity analysis shows that the execution time is nearly linearly dependent on the number of nodes in sparse networks. We finally give demonstrative applications of the algorithm to a set of synthetic benchmark networks and also real-world networks to verify the algorithmic performance.

Pan–tilt–zoom (PTZ) cameras play an important role in visual surveillance system. Dual‐PTZ camera system is the simplest and most typical one. The superiority of this system lies in that it can obtain both large‐view information and high‐resolution local‐view information of the tracked object at the same time. One method to achieve such task is to use master–slave configuration. One camera (master) tracks moving objects at low resolution and provides the positional information to another camera (slave). Then the slave camera can point towards the object at high resolution and track it dynamically. In this paper, we propose a novel framework exploiting planar ground assumption to achieve cooperative tracking. The approach differs from conventional methods in that we exploit planar geometric constraint to solve the camera collaboration problem. Compared with the existing approach, the proposed framework can be used in the case of wide baseline, and allows the depth change of the tracked object. The proposed method can also adapt to the dynamic change of the surveillance scene. Besides, we also describe a self‐calibration method of homography matrix which is induced by the ground plane between two cameras. We demonstrate the effectiveness of the proposed method by testing it with a tracking system for surveillance applications.

An adaptive shadow detection algorithm is proposed to eliminate interference on object detection from the shadow. The algorithm uses three components in YUV colour space to identify shadow pixels from the candidate foreground. An adaptive threshold estimator is designed to improve shadow detection accuracy and adaptive capacity in various lighting conditions. This estimator uses edge detection method to obtain global texture, as well statistical calculations to obtain the thresholds. Algorithm has the characteristic of low complexity and little restraint; hence it is suitable for real time‐moving shadow detection in various lighting conditions. Experiment results show that this algorithm can obtain a high detection accuracy and the time‐assume is greatly shortened compared with other algorithms with similar accuracy.

Accurate high resolution LAI reference maps are necessary for the validation of coarser resolution satellite derived LAI products. In this paper, an efficient method for combining field observations and Landsat ETM+ derived LAI is proposed based on the Bayesian Maximum Entropy paradigm to get more accurate reference maps. This method can take account of the uncertainties associated with field observations and linear relationship between the ETM+ LAI and in situ measurements to perform a nonlinear prediction of the interest variable. A comparison with ETM+ derived LAI surfaces in three validation sites from the BIGFOOT project showed that the RMSE can be reduced by this approach, indicating a promising method in fusing different sources and different types of data.

Land surface temperature (LST) at both high spatial and high temporal resolution is required for routine monitoring of surface energy fluxes. Disaggregating LST to the NDVI-pixel resolution is possible because of significant inverse relationship between LST and vegetation indices. A modified algorithm (SWISF) has been proposed for thermal imagery sharpening, in which multiple least-squares regression relationships between LST and vegetation indices were acquired for bins of pixels with different soil wetness index values. Applying both SWISF and Distrad which is originally proposed by Kustas et al. to simulated thermal maps at 360 m resolution and sharpening down to 90 m shows that the new algorithm slightly outperform the old one. Moreover, DisTrad does not have the ability to consider the fact that two pairs of pixels with the same NDVI difference may have distinct LST difference under different soil moisture conditions, while SWISF algorithm could consider it to some extent.

Multirate arrays where the data transmission rate at different paths varies are introduced. Using a multirate clock, transparent data or data with small delays are propagated K times faster than the computed data, achieving a speedup of a factor of K as compared to systolic arrays. A new synthesis method for a class of nonuniform recurrence equations named DURE (directional uniform recurrence equations) for multirate arrays is introduced. The synthesis method consists of obtaining the DURE from the initial algorithm and finding the symmetric plane, the schedule vector, and the projection vector.>