Unsupervised graph anomaly detection (GAD) has received increasing attention in recent years. It aims to identify anomalous data patterns using only unlabeled node information from graph-structured data. However, prevailing unsupervised GAD methods typically assume complete node attributes and structural information-a condition that is seldom satisfied in real-world scenarios due to privacy constraints, collection errors, or dynamic node arrivals. Standard imputation strategies risk "repairing" rare anomalous nodes so that they appear normal, thereby introducing imputation bias into the detection process. Moreover, when both node attributes and edges are missing simultaneously, estimation errors in one view can contaminate the other, causing cross-view interference that further degrades detection performance. To address these challenges, we propose M²V-UGAD, a multiple-missing-values-resistant unsupervised GAD framework for incomplete graphs. Specifically, we introduce a dual-pathway encoder that independently reconstructs missing node attributes and graph structure, preventing errors in one view from propagating to the other. The two pathways are then fused and regularized within a joint latent space such that normal nodes occupy a compact inner manifold while anomalies lie on an outer shell. Finally, to mitigate imputation bias, we sample latent codes just outside the normal region and decode them into realistic node features and subgraphs, yielding hard negative examples that sharpen the decision boundary. Experiments on seven public benchmarks show that M²V-UGAD consistently outperforms existing unsupervised GAD methods across a range of missing rates.

Label propagation has been widely used to enhance performance for clustering. Many semi-supervised non-negative matrix factorization (NMF) methods based on label propagation have been proposed. However, these methods mainly pay attention to learning a label prediction matrix, neglecting the efficient learning of a low-dimensional representation of original data. Additionally, they lead to inconsistent structures with NMF when leveraging label constraints, compromising the learning performance for low-dimensional representation and basis matrix. To address these problems, this paper proposes a novel semi-supervised NMF method named semi-supervised non-negative matrix factorization with weighted label propagation (SNMFWLP). Firstly, SNMFWLP considers an orthogonal constraint on basis matrix to minimize the redundancy in the process of decomposition in NMF. Secondly, SNMFWLP introduces a weighted label propagation model into NMF to learn an efficient low-dimensional representation used as label prediction matrix. The weighted label propagation model not only propagates label information but also maintains the structures consistent with structures of NMF, beneficial to a consistent low-dimensional representation. Additionally, effective algorithm and convergence analysis are also presented. Finally, numerous experiments on real-world data sets are conducted to demonstrate the superiority of the proposed method in comparison to several state-of-the-art unsupervised and semi-supervised NMF methods.

Diffusion-based image generation has proliferated, making robust detection of synthetic imagery critical. We propose a background-noise-driven detector motivated by the observation that real camera images preserve physical noise traces, whereas model-generated images tend to exhibit algorithm-induced residual statistics. Starting from sRGB, we apply a deterministic inverse ISP to obtain an approximate Bayer RAW representation, train a lightweight RAW-domain denoiser, and extract a noise residual by subtracting the denoised reconstruction from the inverse-ISP signal. A detector trained only on ADM residuals generalizes in a zero-shot manner to a wide range of unseen diffusion generators. By emphasizing noise-domain cues rather than semantic content, the proposed method offers a simple and practical approach to diffusion-generated image detection.

In the present environment where privacy protection is increasingly emphasized, source-free unsupervised domain adaptation (SFUDA) has garnered more attention compared to standard unsupervised domain adaptation (UDA). It concentrates on transferring knowledge directly from well-trained source models to unlabeled target domains without requiring the involvement of source domain like UDA, greatly enhancing data protection capabilities. Many existing methods employ pseudo-labeling to guide this process, but due to domain shift, pseudo-labels often introduce significant noise. Although there are methods to filter out this noise and mitigate its impact, they may also result in the loss of crucial sample knowledge, leading to performance deterioration. In contrast, we propose a novel approach called Progressive Curriculum Learning with Teacher-Student Collaboration (PCTSC) method to mitigate the adverse influence of noisy labels in SFUDA. Inspired by curriculum learning, PCTSC assesses samples’ learning difficulty and trains models in an incremental manner from easy to hard, thereby enhancing the capability of model to against noise. Furthermore, PCTSC employs a two-stage learning approach: initially, a teacher model directs the student model, and later, the student model transitions to independent learning. We assess the effectiveness of PCTSC by conducting extensive experiments across three benchmark datasets, demonstrating its robustness against pseudo-label noise in SFUDA setting.

Fuzzy logic-based graph neural networks (FL-GNN) have recently garnered growing attention in node classification, which aims to enhance the ability of GNN in modeling uncertain relationships between nodes. However, existing FL-GNN typically assume that nodes in the source domain (training set) and target domain (test set) follow the identical data distribution and class sets. Real-world scenarios often exhibit significant distribution shifts and target domain even contains classes that were not present in the source domain, termed open-set cross-domain node classification (OSCD-NC), which seriously damages their superior performance. Thus, how to leverage the strong uncertain knowledge representation capacity of FL-GNN to learn a well-defined boundary between seen and unseen classes for improving OSCD-NC performance remains an open and underexplored research problem. In this paper, we propose an effective domain-adaptive fuzzy graph diffusion network (DFGDN) for OSCD-NC. Specifically, with the help of a fuzzy adjacency matrix, fuzzy graph diffusion networks are proposed to generate robust fuzzy node representations by adaptively enhancing feature collaboration between low-pass and high-pass graph filters. Then, a peer ($M$+1)-class classifier is introduced to learn a rough class boundary by measuring their class prediction probability difference for target domain. After that, the ($M$+1)-means clustering and decoder modules are simultaneously designed to discover more supervision guidance from target domain for learned class boundary optimization. Finally, we jointly optimize the above modules in an adversarial manner via classification loss, classifier discrepancy loss and mean squared error loss, which further improves the accuracy of the learned class boundary by pulling seen nodes from the source domain and target domain closer, and pushing unseen nodes away. Extensive experiments on three cross-domain data pairs and various openness rates demonstrate the effectiveness of the proposed DFGDN framework.

Graphs play a pivotal role in multimedia applications by integrating information to model complex relationships. Recently, graph class-incremental learning (GCIL) has garnered attention, allowing graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge while retaining knowledge of old classes. Existing GCIL methods primarily focus on a closed-set assumption, where all test samples are presumed to belong to previously known classes. Such assumption restricts their applicability in real-world scenarios, where unknown classes naturally emerge during inference, and are absent during training. In this paper, we explore a more challenging open-set graph class-incremental learning scenario with two intertwined challenges: catastrophic forgetting of old classes, which impairs the detection of unknown classes, and inadequate open-set recognition, which destabilizes the retention of learned knowledge. To address the above problems, a novel OGCIL framework is proposed, which utilizes pseudo-sample embedding generation to effectively mitigate catastrophic forgetting and enable robust detection of unknown classes. To be specific, a prototypical conditional variational autoencoder is designed to synthesize node embeddings for old classes, enabling knowledge replay without storing raw graph data. To handle unknown classes, we employ a mixing-based strategy to generate out-of-distribution (OOD) samples from pseudo in-distribution and current node embeddings. A novel prototypical hypersphere classification loss is further proposed, which anchors in-distribution embeddings to their respective class prototypes, while repelling OOD embeddings away. Instead of assigning all unknown samples into one cluster, our proposed objective function explicitly models them as outliers through prototype-aware rejection regions, ensuring a robust open-set recognition. Extensive experiments on five benchmarks demonstrate the effectiveness of OGCIL over existing GCIL and open-set GNN methods.

WiFi channel state information (CSI)-based gesture recognition offers unique advantages, including cost-effectiveness and enhanced privacy protection, and has garnered significant attention in recent years. However, existing WiFi-based gesture recognition solutions exhibit poor generalization ability when deployed in new environment, orientation, or location. Although some methods combine labeled source domain and unlabeled target domain to learn domain-independent features, factors, such as data privacy protection, hinder access to source data during practical environment adaptation. Consequently, we consider realistic scenario where source data is unavailable during adaptation of unlabeled test data, and instead, a trained source domain model is used. In this article, we propose Wi-SFDAGR, a WiFi-based source-free domain adaptation gesture recognition framework. Specifically, we treat cross-domain as an unsupervised clustering problem, aiming to ensure that features within local neighborhoods exhibit similar prediction results while those farther apart display different prediction outcomes in the feature space. We theoretically analyze the effect of enhanced prediction consistency between neighbor points extracted from gestures on generalization error. Furthermore, we employ an attraction-dispersion network to strengthen prediction consistency among closely located features in the feature space while reducing it for distantly located features. To mitigate noise introduced during nearest neighbor sample selection in the feature space (where predictions may not align with the input sample’s prediction), we progressively improve nearby sample feature aggregation by estimating uncertainty to reweight local neighborhood predictions. Finally, extensive experiments are conducted on the Widar 3.0 and XRF55 datasets and the results show our proposed framework outperforms most cross-domain methods.

Sequential recommendation seeks to understand user preferences based on their past actions and predict future interactions with items. Recently, several techniques for sequential recommendation have emerged, primarily leveraging graph convolutional networks (GCNs) for their ability to model relationships effectively. However, real-world scenarios often involve sparse interactions, where early and recent short-term preferences play distinct roles in the recommendation process. Consequently, vanilla GCNs struggle to effectively capture the explicit correlations between these early and recent short-term preferences. To address these challenges, we introduce a novel approach termed Graph Convolutional Networks with Collaborative Feature Fusion (COFF). Specifically, our method addresses the issue by initially dividing each user interaction sequence into two segments. We then construct two separate graphs for these segments, aiming to capture the user's early and recent short-term preferences independently. To obtain robust prediction, we employ multiple GCNs in a collaborative distillation manner, incorporating a feature fusion module to establish connections between the early and recent short-term preferences. This approach enables a more precise representation of user preferences. Experimental evaluations conducted on five popular sequential recommendation datasets demonstrate that our COFF model outperforms recent state-of-the-art methods in terms of recommendation accuracy.

Remote sensing data from real-world scenarios manifests a long-tailed distribution, with the continuous emergence of new classes over time. Nevertheless, the existing class-incremental remote sensing classification models neglect the above long-tailed distribution phenomenon, which seriously damages their overall superior performance. Meanwhile, long-tail class-incremental learning developed in other areas focuses only on the classifier decision boundary optimization of the tail-class, while neglecting the robustness of the feature backbone. The feature backbone trained on the base classes causes a serious significant distribution shift for the incremental classes owing to the distributional differences between base and incremental classes. To solve these issues, we propose a continually evolved feature and classifiers learning (CEF-CL) framework for long-tail class-incremental remote sensing scene classification. Specifically, tail-class data are scaled and grafted onto head-class data to diversify the semantic information of the tail-class leveraging the rich context of the head classes, which can improve the generalization of the feature backbone. And then, an adaptive multi-scale feature fusion (AMFF) module is proposed to couple feature maps of head and tail classes scale by scale for generating virtual tail-class features that deeply perceive head-class information, which can further enhance the reliability of classifier decision boundary optimization. Furthermore, examples from old classes are regarded as pseudo-tail classes to participate in incremental learning, which greatly alleviates catastrophic forgetting of old classes. Extensive experiments on two remote sensing benchmarks demonstrate the superiority of the proposed CEF-CL in comparison with existing class-incremental learning.

Abstract In recent years, facial prior has been widely applied to enhance the quality of super-resolution (SR) facial images in face super-resolution (FSR) methods based on deep learning. However, most of the existing facial prior-based FSR methods have insufficient attention to local texture details, which can cause the generated SR facial images with overly smooth and unrealistic texture details, and show obvious artifacts under large magnification. With the help of GAN prior, recent advances can produce excellent results in terms of fidelity and realness. A generative framework for FSR is proposed in this work, which combines GAN and facial prior, termed CFGPFSR. Firstly, we pre-train a face StyleGAN2 and a face parsing network (FPN) that can generate decent parsing maps, in which the proposed CFGPFSR exploits rich and varied priors encapsulated in the face StyleGAN2 (GAN prior) and face parsing maps extracted from the FPN (facial prior) for FSR. Moreover, we introduce the Channel-Split Spatial Feature Transform (CS-SFT) method to further improve FSR performance. GAN and facial priors are introduced into the FSR process through the designed CS-SFT layers so that SR facial images obtain a promising balance between fidelity and realness. Unlike GAN inversion methods which necessitate costly image optimization at runtime, the proposed CFGPFSR can jointly recover facial details by only utilizing one forward pass. Experimental results on synthetic and real images indicate that the proposed CFGPFSR obtains remarkable performance in 16 × SR task, and some of its metrics such as peak signal to noise ratio (PSNR) and structural similarity (SSIM) are higher than that of the comparison methods. Meanwhile, it shows impressive results in reconstructing high-quality facial images.

The application of Auto-Encoder (AE) to multi-view representation learning has gained traction due to advancements in deep learning. While some current AE-based multi-view representation learning algorithms incorporate the geometric structure of the input data into their feature representation learning process, their use of a shallow structured graph regularization term can be restrictive when used in conjunction with deep models. Furthermore, current multi-view representation learning algorithms do not fully utilize the diversity and consistency presented in different views, leading to a reduction in the efficacy of feature learning. This paper introduces a novel approach, reconstructed graph constrained auto-encoders (RGCAE), for multi-view representation learning. Unlike existing methods, our approach incorporates deep adaptive graph regularization based on multi-layer perceptron to ensure the preservation of the geometric similarity graph, which is constructed based on the local invariance principle. By decoupling the feature representation learning from the preservation of the geometric structure among different views, our approach can better leverage the diversity presented in multi-view data. We obtain view-specific representations that preserve the geometric structure and then combine them by averaging to obtain a common representation. To ensure the consistency of the multi-view data, we minimize the loss between the view-specific and common representations. Consequently, our RGCAE approach can maintain the geometric structure of multi-view data and is better suited for integration with deep models. Extensive experiments on six datasets demonstrate that RGCAE obtained promising performance, compared with the state-of-the-art methods.

Lightweight semantic segmentation plays an essential role in image signal processing that is beneficial to many multimedia applications, such as self-driving, robotic vision, and virtual reality. Due to the powerful capability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years for semantic segmentation. In spite of achieving remarkable progresses, they often ignore semantic context ranged from different scales. Furthermore, most of them always neglect the object boundaries, serving as a significant assistance for lightweight semantic segmentation. To alleviate these problems, this paper develops a Boundary-guide dual-resolution lightweight network with multi-scale Semantic Context, called BSCNet, for semantic segmentation. Specifically, to enhance the capability of feature representation, an Extremely Lightweight Pyramid Pooling Module (ELPPM) is designed to capture multi-scale semantic context at the top of low-resolution branch of BSCNet. In addition, to increase feature similarity of the same object while keeping feature discrimination of different objects, pixel information is propagated throughout the entire object area using a simple Boundary Auxiliary Fusion Module (BAFM), where the predicted object boundaries are served as high-level guidance to refine low-level convolutional features. The comprehensive experimental results have demonstrated that our BSCNet is simple and effective, achieving state-of-the-art trade-off in terms of segmentation accuracy and running efficiency on CityScapes, CamVid, and KITTI datasets.

Recently, model compression has been widely used for the deployment of cumbersome deep models on resource-limited edge devices in the performance-demanding industrial Internet of Things (IoT) scenarios. As a simple yet effective model compression technique, knowledge distillation (KD) aims to transfer the knowledge (e.g., sample relationships as the relational knowledge) from a large teacher model to a small student model. However, existing relational KD methods usually build sample correlations directly from the feature maps at a certain middle layer in deep neural networks, which tends to overfit the feature maps of the teacher model and fails to address the most important sample regions. Inspired by this, we argue that the characteristics of important regions are of great importance, and thus, introduce attention maps to construct sample correlations for knowledge distillation. Specifically, with attention maps from multiple middle layers, attention-based sample correlations are newly built upon the most informative sample regions, and can be used as an effective and novel relational knowledge for knowledge distillation. We refer to the proposed method as multilevel attention-based sample correlations for knowledge distillation (or MASCKD). We perform extensive experiments on popular KD datasets for image classification, image retrieval, and person reidentification, where the experimental results demonstrate the effectiveness of the proposed method for relational KD.

Cross-modal hashing is an effective cross-modal retrieval approach because of its low storage and high efficiency. However, most existing methods mainly utilize pre-trained networks to extract modality-specific features, while ignore the position information and lack information interaction between different modalities. To address those problems, in this paper, we propose a novel approach, named cross-modal generation and pair correlation alignment hashing (CMGCAH), which introduces transformer to exploit position information and utilizes cross-modal generative adversarial networks (GAN) to boost cross-modal information interaction. Concretely, a cross-modal interaction network based on conditional generative adversarial network and pair correlation alignment networks are proposed to generate cross-modal common representations. On the other hand, a transformer-based feature extraction network (TFEN) is designed to exploit position information, which can be propagated to text modality and enforce the common representation to be semantically consistent. Experiments are performed on widely used datasets with text-image modalities, and results show that the proposed method achieved competitive performance compared with many existing methods.

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is an emerging research task that aims to retrieve data of new classes across sketches and images. It is challenging due to the heterogeneous distributions and the inconsistent semantics across seen and unseen classes of the cross-modal data of sketches and images. To realize knowledge transfer, the latest approaches introduce knowledge distillation, which optimizes the student network through the teacher signal distilled from the teacher network pre-trained on large-scale datasets. However, these methods often ignore the mispredictions of the teacher signal, which may make the model vulnerable when disturbed by the wrong output of the teacher network. To tackle the above issues, we propose a novel method termed Prototype-based Selective Knowledge Distillation (PSKD) for ZS-SBIR. Our PSKD method first learns a set of prototypes to represent categories and then utilizes an instance-level adaptive learning strategy to strengthen semantic relations between categories. Afterwards, a correlation matrix targeted for the downstream task is established through the prototypes. With the learned correlation matrix, the teacher signal given by transformers pre-trained on ImageNet and fine-tuned on the downstream dataset, can be reconstructed to weaken the impact of mispredictions and selectively distill knowledge on the student network. Extensive experiments conducted on three widely-used datasets demonstrate that the proposed PSKD method establishes the new state-of-the-art performance on all datasets for ZS-SBIR.

Cross-modal hashing that leverages hash functions to project high-dimensional data from different modalities into the compact common hamming space, has shown immeasurable potential in cross-modal retrieval. To ease labor costs, unsupervised cross-modal hashing methods are proposed. However, existing unsupervised methods still suffer from two factors in the optimization of hash functions: 1) similarity guidance, they barely give a clear definition of whether is similar or not between data points, leading to the residual of the redundant information; 2) optimization strategy, they ignore the fact that the similarity learning abilities of different hash functions are different, which makes the hash function of one modality weaker than the hash function of the other modality. To alleviate such limitations, this paper proposes an unsupervised cross-modal hashing method to train hash functions with discriminative similarity guidance and adaptively-enhanced optimization strategy, termed Deep Adaptively-Enhanced Hashing (DAEH). Specifically, to estimate the similarity relations with discriminability, Information Mixed Similarity Estimation (IMSE) is designed by integrating information from distance distributions and the similarity ratio. Moreover, Adaptive Teacher Guided Enhancement (ATGE) optimization strategy is also designed, which employs information theory to discover the weaker hash function and utilizes an extra teacher network to enhance it. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed DAEH against the state-of-the-arts.

Feature representation is highly important for many computer vision tasks. A broad range of prior studies have been proposed to strengthen representation ability of architectures via built-in blocks. However, during the forward propagation, the reduction in feature map scales still leads to the lack of representation ability. In this paper, we focus on boosting the representational power of a convolutional network by the multi-branch framework that we term the BranchNet. Each branch is directly supervised by label information to enrich the hierarchy features in BranchNet. Based on this framework, we further propose a collaborative learning loss and a soft target loss to transfer knowledge from deeper layers to shallow layers. BranchNet is an efficient training framework without extra parameters introduced in inference and can be integrated in existing networks, e.g., VGG, ResNet, and DenseNet. We evaluate BranchNet on all of these models and find that our method outperforms the baseline models on the widely-used CIFAR and ImageNet datasets. In particular, on the CIFAR-100 dataset, the classification error of ResNet-164 with BranchNet decreases by 4.51 percent. We also conduct experiments on the representative computer vision tasks of instance segmentation and class activation mapping, further verifying the superiority of BranchNet over the baseline models. Models and code are available athttps://github.com/zyyupup/BranchNet/.

The task of audio-visual event localization (AVEL) aims to localize a visible and audible event in a video. Previous methods first divide a video into segments and then fuse visual and acoustic features at the segment level via a co-attention mechanism. However, existing methods mostly model relations between individual visual and audio segments in a limitedly short period, which may not cover a longer video duration for better high-level event information modeling. In this paper, we proposed a novel model termed Multimodal Transformer Network with Latent Interaction (MTNLI) to tackle this problem. The proposed MTNLI model employs a multimodal Transformer structure to learn the cross-modality relationships between latent visual and audio summarizations in long segment sequences, which summarize the visual and audio segments into a small number of latent representations to avoid modeling uninformative individual visual-audio relations. The cross-modality information between the latent summarizations is propagated to fuse valuable information from both modalities, which can effectively handle large temporal inconsistent between vision and audio. Our MTNLI method achieves state-of-the-art performance on the benchmark AVE (Audio-Visual Event) dataset for the event localization task.

Summary In this paper, a dual switching discrete‐time linear system, simultaneously subject to deterministic switching and Markov chain, is considered. This study does not consider the transition probability of the Markov chain as fixed but determined by the current position of deterministic switching. Namely, such dual switching discrete‐time linear system is composed of a family of discrete‐time Markov jump systems and follows a rule that directs the switching sequences between them. The exponentially almost sure stability problem, for dual switching discrete‐time linear system with exponential uncertainty, is addressed by using persistent dwell time and stochastic multi‐Lyapunov function. The sufficient conditions for the exponentially almost sure stability of dual switching discrete‐time linear system are expressed as linear matrix inequalities. Finally, a simulation example demonstrates the validity of the derived results.

Fully convolutional neural networks (FCNs) have shown great success in dense estimation tasks. One key pillar of such progress is mining multi-scale context cues from features in different convolutional layers. This paper introduces contextual aggregating network(CAN), a generic convolutional feature ensembling framework for semantic segmentation. Our framework first captures multi-scale contextual clues by concatenating multi-level feature representation, which carries both coarse semantics and fine details. Then it adaptively integrates stacked features to perform dense pixel estimation. The proposed CAN is trainable end-to-end, and allows us to fully investigate multi-scale context information embedded in images. The experiments show the promising results of our method on PASCAL VOC 2012 and Cityscapes dataset.

In pattern recognition, the representation-based classification (RBC) has attracted much attention recently. As a representative one of RBC, collaborative representation-based classification (CRC) and its variants have achieved promising classification performance in many visual classification tasks. However, most of the CRC methods cannot directly consider the class discrimination information of data that is very important for classification. To fully use the class discrimination information, we propose a novel discriminative group collaborative competitive representation-based classification method (DGCCR) in this paper. In the designed DGCCR model, the discriminative competitive relationships of classes, the discriminative decorrelations among classes and the weighted class-specific group constraints are simultaneously taken into account for strengthening the power of pattern discrimination. Experiments on three visual classification data sets demonstrate that the proposed DGCCR out-performs state-of-the-art RBC methods.

With the increasing availability of multiview nonnegative data in real applications, multiview representation learning based on nonnegative matrix factorization (NMF) has attracted more and more attentions. However, existing NMF-based methods are sensitive to noises and are difficult to generate discriminative features with noisy views. To address these problems, we propose a co-regularized multiview nonnegative matrix factorization method with correlation constraint for nonnegative representation learning, which jointly exploits consistent and complementary information across different views. Different from previous works, we aim at integrating information from multiple views efficiently and making it more robust to the presence of noisy views. More specifically, we exploit the complementary information of multiple views through the co-regularization to accommodate the presence of the noisy views. Meanwhile, correlation constraint is imposed on the low-dimensional space to learn a common latent representation shared by different views. For the induced objective function, we derive an alternative algorithm to solve the optimization problem. The experimental results on four real datasets demonstrate the effectiveness and robustness of the proposed algorithm.

In this paper, we address the problem of signal detection in multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) system by using auto-encoder (AE) network and extreme learning machine (ELM). The existing signal detection algorithms, such as zero-forcing successive-interference-cancellation (ZF-SIC), minimum-mean-square-error successive-interference-cancellation (MMSE-SIC), maximum likelihood detection (MLD) and quantum-genetic radial-basis-function (QGA-RBF) etc., haven't considered the characteristics invariance of signals in the process of transmission. Combined AE network with ELM, a novel signal detection scheme for MIMO-OFDM system is proposed. The proposed algorithm can obtain the features of received signals effectively through AE and recognize the corresponding original signals quickly via ELM. Moreover, the channel matrix is not required in the process of signal detection. We have derived a theoretically model and analyze the feasibility of feature extraction in received signals, and simulations are also carried out to evaluate the performance and compare that with some traditional and state-of-the-art algorithms. The simulation results confirm that the performance of the proposed scheme outperforms that of many detection schemes such as zero-forcing (ZF), ZF-SIC, minimum-mean-square-error (MMSE), MMSE-SIC, and reaches the similar bit-error-rate (BER) performance of MLD and QGA-RBF with much lower complexity.

In this paper, we investigate the problem of personalized ranking from implicit feedback (PRIF). It is a more common scenario (e.g. purchase history, click log and page visitation) in recommender systems. The training data are only binary in these problems, reflecting the users’ actions or inactions. One shortcoming of previous PRIF algorithms is noise sensitivity: outliers in training data might bring significant fluctuations in the training process and lead to inaccuracy of the algorithm. In this paper, we propose two robust PRIF algorithms to solve the noise sensitivity problem of existing PRIF algorithms by using the pairwise sigmoid and pairwise fidelity loss functions. These two pairwise loss functions are flexible and can easily be adopted by popular collaborative filtering models such as the matrix factorization (MF) model and the K-nearest-neighbor (KNN) model. A learning process based on stochastic gradient descent with bootstrap sampling is utilized for the optimization. Experiments are conducted on practical datasets containing noisy data points or outliers. Results demonstrate that the proposed algorithms outperform several state-of-the-art one class collaborative filtering (OCCF) algorithms on both the MF and KNN models over different evaluation metrics.

Kernel methods provide an efficient nonparametric model to produce adaptive nonlinear filtering (ANF) algorithms. However, in practical applications, standard squared error based kernel methods suffer from two main issues: (1) a constant step size is used, which degrades the algorithm performance in non-stationary environment, and (2) additive noises are assumed to follow Gaussian distribution, while in practice the noises are generally non-Gaussian and follow other statistical distributions. To address these two issues simultaneously, this paper proposes a novel kernel normalized mixed-norm (KNMN) algorithm. Compared to the standard squared error based kernel methods, the KNMN algorithm extends the linear mixed-norm adaptive filtering algorithms to Reproducing Kernel Hilbert Space (RKHS) and introduces a normalized step size as well as adaptive mixing parameter. We also conduct the mean square convergence analysis and demonstrate the desirable performance of the KNMN algorithm in solving the system identification problem.

Non-contact face-video based human heart rate (HR) estimation has attracted a lot of attentions in recent years. Almost all the state-of-the-art webcam or smartphone based HR estimation methods comprise three main steps: firstly, a region of interest (ROI) on the human face is detected in each video frame, then, the target signal is obtained by fusing multiple raw traces, which are extracted from the RGB channels across all the video frames, finally, HR is estimated by applying frequency analysis approach to the target signal. However, three major drawbacks impede the applicability of the current methods: (1) the performance of ROI detection is susceptible to head motion and facial expression, (2) there is still a lack of well-accepted method for fusing raw traces to form the target signal, and (3) the adopted frequency analysis approaches always provide estimation results with low resolution and high side lobes. To address these issues, we propose a novel HR estimation method which is applicable to ordinary cameras subject to natural head movement or facial expression. The proposed method features ROI detection via facial feature detection and tracking, target signal extraction via Independent Component Analysis (ICA) in the RGB channels, and HR estimation via real-valued iterative adaptive approach (RIAA). Experimental results validate the superiority of our proposed method.

Dimensionality reduction is an important method to analyze high-dimensional data and has many applications in pattern recognition and computer vision. In this paper, we propose a robust nonnegative patch alignment for dimensionality reduction, which includes a reconstruction error term and a whole alignment term. We use correntropy-induced metric to measure the reconstruction error, in which the weight is learned adaptively for each entry. For the whole alignment, we propose locality-preserving robust nonnegative patch alignment (LP-RNA) and sparsity-preserviing robust nonnegative patch alignment (SP-RNA), which are unsupervised and supervised, respectively. In the LP-RNA, we propose a locally sparse graph to encode the local geometric structure of the manifold embedded in high-dimensional space. In particular, we select large p -nearest neighbors for each sample, then obtain the sparse representation with respect to these neighbors. The sparse representation is used to build a graph, which simultaneously enjoys locality, sparseness, and robustness. In the SP-RNA, we simultaneously use local geometric structure and discriminative information, in which the sparse reconstruction coefficient is used to characterize the local geometric structure and weighted distance is used to measure the separability of different classes. For the induced nonconvex objective function, we formulate it into a weighted nonnegative matrix factorization based on half-quadratic optimization. We propose a multiplicative update rule to solve this function and show that the objective function converges to a local optimum. Several experimental results on synthetic and real data sets demonstrate that the learned representation is more discriminative and robust than most existing dimensionality reduction methods.

Object detection has been widely studied in the computer vision community and it has many real applications, despite its variations, such as scale, pose, lighting, and background. Most classical object detection methods heavily rely on category-based training to handle intra-class variations. In contrast to classical methods that use a rigid category-based representation, exemplar-based methods try to model variations among positives by learning from specific positive samples. However, current existing exemplar-based methods either fail to use any training information or suffer from a significant performance drop when few exemplars are available. In this paper, we design a novel local metric learning approach to well handle exemplar-based object detection task. The main works are two-fold: 1) a novel local metric learning algorithm called exemplar metric learning (EML) is designed and 2) an exemplar-based object detection algorithm based on EML is implemented. We evaluate our method on two generic object detection data sets: UIUC-Car and UMass FDDB. Experiments show that compared with other exemplar-based methods, our approach can effectively enhance object detection performance when few exemplars are available.