The prediction of future trajectories for vehicle in the field of autonomous driving is of utmost importance to ensure safe driving. However, it is challenging as the existing methods still suffer from noise sensitivity, limited representation ability and time-consuming inference. To this end, we propose a novel Driving Mode Centric Denoising Diffusion Model for trajectory prediction, namely DMC-Diffuser. Specifically, we first devise a driving mode token generator by utilizing different time-scale information from noisy trajectories. Subsequently, we employ an attention-based denoiser, which leverages the driving mode token along with the driving context to learn the potential trajectories. Furthermore, aided by a flexible denoiser structure with an accelerated sampling algorithm, the proposed method can achieve the comparable performance at the cost of low-complexity inference. Experimental results on two datasets show that DMC-Diffuser has achieved superior performance compared to the state-of-the-art methods, e.g., a comprehensive performance gain of nearly 9% over other diffusion based methods.

The powerful capability of HyperGraph Neural Networks (HGNNs) in modeling intricate, high-order relationships among multiple data samples stems primarily from their ability to aggregate both the direct neighborhood features of individual nodes and those associated with hyperedges. However, the limited scope of feature propagation in existing HGNNs significantly reduces the utilization of hypergraph information, exacerbating over-squashing and over-smoothing issues. To this end, we propose a novel K-hop HyperGraph Neural Network (KHGNN) to facilitate the interactions of distant nodes and hyperedges. Specifically, the bisection nested convolution based on HyperGINE is employed to extract features from nodes, hyperedges, and structures along all shortest paths between nodes or hyperedges, providing representations of long-distance relationships. With these comprehensive path features, nodes and hyperedges are guided to aggregate distant information while learning their complex relationships. The extensive experiments, particularly on long-range graph datasets, demonstrate that the proposed method achieves SOTA performance compared to existing HGNNs and graph neural networks.

Multiview representation learning has recently attracted significant attention in the machine learning and computer vision community. However, during fusing information from multiple views, existing work often neglect to exploit the complementary information in each view and endow with the interpretability of model. To this end, in this article, we propose a multiview attention fusion information bottleneck network, termed by MVAIBNet. Specifically, MVAIBNet deliberately develops dual-path reconstructions to extract latent embeddings of views, where view-peculiar representations are disentangled from the embeddings using$\beta$-VAE, to help reconstruct each view. Then, to align and fuse view-common representations, an attention fusion unit, namely the multiview channel fusion unit (MVCFU), is presented accordingly. Furthermore, relying on the information bottleneck principle, we integrate the consistency information and specificity information of the views to prompt a compact semantic representation of multiple views with balancing the complementarity and consistency among multiple views flexibly. Extensive experimental results on four real-world datasets show that our algorithm achieves encouraging performance on several evaluation metrics compared to the state-of-the-art methods.

Multiview clustering (MVC) is a fundamental research topic in the field of machine learning and data mining, which has been developed rapidly and made significant progress recently. However, the current works tend to learn the individual representation of each view and then naviely merge or align them to achieve a shared representation of multiview data. By doing this, they often ignore the interference caused by the entanglement among multiple views, leading to the shared latent embedding cannot well model the correlation of all views. To this end, in this article, we propose a novel self-supervised adversarial learning-based view-common latent autoencoders for MVC, termed by multi-SSALvcAE. Specifically, the proposed method can effectively disentangle the unique and common information of each view by virtue of multiview adversarial latent autoencoders. And then only the common parts are fused to form the shared information, after being aligned deliberately on multiview semantic space. Experimental results show that our method achieved the promising results on several datasets, against the state-of-the-arts.

Recently, multivariate time series (MTS) clustering has gained lots of attention. However, state-of-the-art algorithms suffer from two major issues. First, few existing studies consider correlations and redundancies between variables of MTS data. Second, since different clusters usually exist in different intrinsic variables, how to efficiently enhance the performance by mining the intrinsic variables of a cluster is challenging work. To deal with these issues, we first propose a variable-weighted K-medoids clustering algorithm (VWKM) based on the importance of a variable for a cluster. In VWKM, the proposed variable weighting scheme could identify the important variables for a cluster, which can also provide knowledge and experience to related experts. Then, a Reverse nearest neighborhood-based density Peaks approach (RP) is proposed to handle the problem of initialization sensitivity of VWKM. Next, based on VWKM and the density peaks approach, an ensemble Clustering framework (SSEC) is advanced to further enhance the clustering performance. Experimental results on ten MTS datasets show that our method works well on MTS datasets and outperforms the state-of-the-art clustering ensemble approaches.

Clustering multi-view data has been a fundamental research topic in the computer vision community. It has been shown that a better accuracy can be achieved by integrating information of all the views than just using one view individually. However, the existing methods often struggle with the issues of dealing with the large-scale datasets and the poor performance in reconstructing samples. This paper proposes a novel multi-view clustering method by learning a shared generative latent representation that obeys a mixture of Gaussian distributions. The motivation is based on the fact that the multi-view data share a common latent embedding despite the diversity among the various views. Specifically, benefitting from the success of the deep generative learning, the proposed model can not only extract the nonlinear features from the views, but render a powerful ability in capturing the correlations among all the views. The extensive experimental results on several datasets with different scales demonstrate that the proposed method outperforms the state-of-the-art methods under a range of performance criteria.

Subspace clustering aims to separate the data into clusters under the hypothesis that the samples within the same cluster will lie in the same low-dimensional subspace. Due to the tough pairwise constraints, k-subspace clustering is sensitive to outliers and initialization. In this letter, we present a novel deep architecture for k-subspace clustering to address this issue, called as Deep Weighted k-Subspace Clustering (DWSC). Specifically, our framework consists of autoencoder and weighted k-subsapce network. We first use the autoencoder to non-linearly compress the samples into the low-dimensional latent space. In the weighted k-subspace network, we feed the latent representation into the assignment network to output soft assignments which represent the probability of data belonging to the according subspace. Subsequently, the optimal k subspaces are identified by minimizing the projection residuals of the latent representations to all subspaces, using the learned soft assignments as a weighting vector. Finally, we jointly optimize the representation learning and clustering in a unified framework. Experimental results show that our approach outperforms the state-of-the-art subspace clustering methods on two benchmark datasets.

The ubiquitous information from multiple-view data, as well as the complementary information among different views, is usually beneficial for various tasks, for example, clustering, classification, denoising, and so on. Multiview subspace clustering is based on the fact that multiview data are generated from a latent subspace. To recover the underlying subspace structure, a successful approach adopted recently has been sparse and/or low-rank subspace clustering. Despite the fact that existing subspace clustering approaches may numerically handle multiview data, by exploring all possible pairwise correlation within views, high-order statistics that can only be captured by simultaneously utilizing all views are often overlooked. As a consequence, the clustering performance of the multiview data is compromised. To address this issue, in this paper, a novel multiview clustering method is proposed by using t-product in the third-order tensor space. First, we propose a novel tensor construction method to organize multiview tensorial data, to which the tensor-tensor product can be applied. Second, based on the circular convolution operation, multiview data can be effectively represented by a t-linear combination with sparse and low-rank penalty using "self-expressiveness." Our extensive experimental results on face, object, digital image, and text data demonstrate that the proposed method outperforms the state-of-the-art methods for a range of criteria.

By using a sparse representation or low-rank representation of data, the graph-based subspace clustering has recently attracted considerable attention in computer vision, given its capability and efficiency in clustering data. However, the graph weights built using the representation coefficients are not the exact ones as the traditional definition is in a deterministic way. The two steps of representation and clustering are conducted in an independent manner, thus an overall optimal result cannot be guaranteed. Furthermore, it is unclear how the clustering performance will be affected by using this graph. For example, the graph parameters, i.e., the weights on edges, have to be artificially pre-specified while it is very difficult to choose the optimum. To this end, in this paper, a novel subspace clustering via learning an adaptive low-rank graph affinity matrix is proposed, where the affinity matrix and the representation coefficients are learned in a unified framework. As such, the pre-computed graph regularizer is effectively obviated and better performance can be achieved. Experimental results on several famous databases demonstrate that the proposed method performs better against the state-of-the-art approaches, in clustering.

Previous work on image clustering focused on seeking a low-dimensional structure from the high-dimensional image data by a shallow linear model, such as sparse subspace clustering (SSC) or low-rank representation (LRR). The recent advance of deep learning shows its superiority via handling data with nonlinear structure, i.e., sparse auto-encoder and independent subspace analysis(ISA), etc. However, most of this type of methods may ignore lots of useful information embedded in the original data. To this end, we propose a novel unsuper-vised learning algorithm via ISA incorporating the subspace structure within data. Specifically, we adopt the ISA to learn local translation invariant feature from data and integrate a prior subspace information into the output of the network simultaneously. This method performs an impressive powerful ability to learn the nature of data. By evaluating on public databases, CMU-PIE and ORL, the experimental results show that the proposed approach achieves better clustering results compared with the state-of-the-art ones.

Sparse subspace clustering (SSC), as one of the most successful subspace clustering methods, has achieved notable clustering accuracy in computer vision tasks. However, SSC applies only 10 vector data in Euclidean space. Unfortunately there is still no satisfactory approach to solve subspace clustering by self-expressive principle f or symmetric positive definite (SPD) matrices which is very useful, in computer vision. In this paper, by embedding the SPD matrices into a Reproducing Kernel Hilbert Space (RKHS), a kernel subspace clustering method is constructed un the SPD manifold through an appropriate Log-Euclidean kernel, termed as kernel sparse subspace clustering on the SPD Riemannian manifold(KSSCR). By exploiting the intrinsic Riemannian geometry within data, KSSCR can effectively characterize the geodesic distance between SPD matrices to uncover the underlying subspace structure. Experimental results Oft several famous datasets demonstrate that the proposed method achieves better clustering results than the state-of-the-art approaches.

Low-rank representation (LRR) has recently attracted a great deal of attention due to its pleasing efficacy in exploring low-dimensional subspace structures embedded in data. For a given set of observed data corrupted with sparse errors, LRR aims at learning a lowest-rank representation of all data jointly. LRR has broad applications in pattern recognition, computer vision and signal processing. In the real world, data often reside on low-dimensional manifolds embedded in a high-dimensional ambient space. However, the LRR method does not take into account the non-linear geometric structures within data, thus the locality and similarity information among data may be missing in the learning process. To improve LRR in this regard, we propose a general Laplacian regularized low-rank representation framework for data representation where a hypergraph Laplacian regularizer can be readily introduced into, i.e., a Non-negative Sparse Hyper-Laplacian regularized LRR model (NSHLRR). By taking advantage of the graph regularizer, our proposed method not only can represent the global low-dimensional structures, but also capture the intrinsic non-linear geometric information in data. The extensive experimental results on image clustering, semi-supervised image classification and dimensionality reduction tasks demonstrate the effectiveness of the proposed method.

Sequential data are ubiquitous in data analysis. For example hyperspectral data taken from a drill hole in geology, high throughput X-ray diffraction measurements in materials research and EEG brain wave signals in neuroscience. The common feature of sequential data is that they are all acquired subject to one external variable such as location, time or temperature. The data evolve along the direction of that variable through several patterns and the “neighboring” data are very likely to share similar features. The purpose of the segmentation for sequential data is then to identify those sequentially continuous segments/patterns. We approach this problem by adopting the subspace clustering method and propose a novel algorithm called low rank sequential subspace clustering (LRSSC), inspired by another method called spatial subspace clustering (SpatSC). SpatSC finds the subspaces by data self-reconstruction with a sparsity constraint on reconstruction weights and promotes the spatial smoothness of the weights by fusion, the essential part in the fused LASSO. However, the subspace identification capability is limited due to the indeterminacy of the sparse regression in finding suitable samples to linearly reconstruct a given sample. This confuses the graph cut algorithm that produces the final clustering results on the weights. To overcome this drawback, we propose to use the low rank penalty instead of sparsity in learning phase to separate subspaces. This improves the subspace identification as well as the robustness to noise. To demonstrate its effectiveness, we test LRSSC on both simulated and real world data compared with SpatSC and other methods. The proposed algorithm is superior to others when noise level is very high.

In this paper, we study the problem of using contextual data points of a data point for its classification problem. We propose to represent a data point as the sparse linear reconstruction of its context, and learn the sparse context to gather with a linear classifier in a supervised way to increase its discriminative ability. We proposed a novel formulation for context learning, by modeling the learning of context reconstruction coefficients and classifier in a unified objective. In this objective, the reconstruction error is minimized and the coefficient sparsity is encouraged. Moreover, the hinge loss of the classifier is minimized and the complexity of the classifier is reduced. This objective is optimized by an alternative strategy in an iterative algorithm. Experiments on three benchmark data set show its advantage over state-of-the-art context-based data representation and classification methods.

Low-rank representation (LRR) has received considerable attention in subspace segmentation due to its effectiveness in exploring low-dimensional subspace structures embedded in data. To preserve the intrinsic geometrical structure of data, a graph regularizer has been introduced into LRR framework for learning the locality and similarity information within data. However, it is often the case that not only the high-dimensional data reside on a non-linear low-dimensional manifold in the ambient space, but also their features lie on a manifold in feature space. In this paper, we propose a dual graph regularized LRR model (DGLRR) by enforcing preservation of geometric information in both the ambient space and the feature space. The proposed method aims for simultaneously considering the geometric structures of the data manifold and the feature manifold. Furthermore, we extend the DGLRR model to include non-negative constraint, leading to a parts-based representation of data. Experiments are conducted on several image data sets to demonstrate that the proposed method outperforms the state-of-the-art approaches in image clustering.

In this paper, a novel image blocky artifact removal scheme based on low-rank matrix recovery is proposed. The problem of suppressing blocky artifacts is formulated as recovering a low-rank matrix from corrupted observations. During the deblocking processing, we do not directly recover the whole clean image but only its high-frequency component and then synthesize the clean image by incorporating the low-frequency component of blocky image. To take advantage of the low-rank matrix recovery paradigm, we first cluster the similar patches of the high-frequency component of image via local pixel clustering, then the clean high-frequency component of image is recovered by formulating an optimization problem of the nuclear norm and ℓ1-norm. The experimental results show that the proposed algorithm can achieve competitive performance in terms of both quantitative and subjective quality.

Linear Subspace Learning (LSL) has been widely used in many areas of information processing, such as dimensionality reduction, data mining, pattern recognition and computer vision. Recent years have witnessed several excellent extensions of PCA in LSL. One is the recent L1-norm maximization principal component analysis (L1Max-PCA), which aims at learning linear subspace efficiently. L1Max-PCA simply simulates PCA by replacing the covariance with the so-called L1-norm dispersion in the mapped feature space. However, it is difficult to give an intuitive interpretation. In this paper, a novel subspace learning approach based on sparse dimension reduction is proposed, which enforces the sparsity of the mapped data to better recover cluster structures. The optimization problem is solved efficiently via Alternating Direction Method (ADM). Experimental results show that the proposed method is effective in subspace learning.

Image super-resolution means forming high-resolution images from low-resolution images. In this paper, we develop a new approach based on the deep Restricted Boltzmann Machines (RBM) for image super-resolution. The RBM architecture has ability of learning a set of visual patterns, called dictionary elements from a set of training images. The learned dictionary will be then used to synthesize high resolution images. We test the proposed algorithm on both benchmark and natural images, comparing with several other techniques. The visual quality of the results has also been assessed by both human evaluation and quantitative measurement.

Feature extraction is one of the most fundamental problems in face recognition tasks. In this paper, motivated by low-rank representation (LRR) model on exploring the multiple subspace structures of observation data, we propose a double low-rank matrix recovery method to learn low-rank subspaces from face images, where it takes into account the recovery of row space and column space information simultaneously. Applying Augmented Lagrangian Multiplier (ALM), the optimization problem on minimization of nuclear norm is resolved efficiently. By evaluating on public face databases, experimental results show that our proposed method works much better than existing face recognition methods based on feature extraction. It is more robust to outliers, varying illumination and occlusion.