Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains. With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for graph learning. However, current approaches face significant challenges in embedding structural information into LLM-compatible formats, requiring either computationally expensive alignment mechanisms or manual graph verbalization techniques that often lose critical structural details. Moreover, these methods typically require labeled data from source domains for effective transfer learning, significantly constraining their adaptability. We propose STAG, a novel self-supervised framework that directly quantizes graph structural information into discrete tokens using a frozen codebook. Unlike traditional quantization approaches, our method employs soft assignment and KL divergence guided quantization to address the unique challenges of graph data, which lacks natural tokenization structures. Our framework enables both LLM-based and traditional learning approaches, supporting true zero-shot transfer learning without requiring labeled data even in the source domain. Extensive experiments demonstrate state-of-the-art performance across multiple node classification benchmarks while maintaining compatibility with different LLM architectures, offering an elegant solution to bridging graph learning with LLMs.

Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in notable data imbalances. Furthermore, models that are excessively customized and devoid of causal connections further undermine the generalizability and interpretability. To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process. Going beyond this process, we utilize the back-door adjustment to specifically address the sub-regions identified as non-causal in the upstream phase. Specifically, we employ a novel image inpainting technique. By using a fine-tuned unconditional Diffusion Probabilistic Model (DDPM) as the generative prior, we in-fill the masks defined as environmental parts, offering the possibility of reliable extrapolation for potential data distributions. CaPaint overcomes the high complexity dilemma of optimal ST causal discovery models by reducing the data generation complexity from exponential to quasi-linear levels. Extensive experiments conducted on five real-world ST benchmarks demonstrate that integrating the CaPaint concept allows models to achieve improvements ranging from 4.3% to 77.3%. Moreover, compared to traditional mainstream ST augmenters, CaPaint underscores the potential of diffusion models in ST enhancement, offering a novel paradigm for this field. Our project is available at https://anonymous.4open.science/r/12345-DFCC.

Content-based 3D object retrieval is a challenging problem in computer vision and graphics, especially for non-rigid 3D shapes. This article proposes a multiview-based robust point representation approach for 3D non-rigid shape retrieval. First, we propose an efficient local descriptor called the local point histogram, which is robust to non-rigid changes in shape. Second, we encode local point histogram features into high-level point features (HPF) using Fisher vectors. Finally, we present an efficient feature fusion method that can further enhance the performance of 3D non-rigid shape retrieval. We extensively tested our approach on two benchmark 3D non-rigid shape datasets, including the SHREC2015 non-rigid shape and SHREC2015 canonical forms. Our method achieves 98.33% and 90.55% retrieval accuracy on the SHREC2015 non-rigid shape and SHREC2015 canonical forms datasets, surpassing previous state-of-the-art methods by nearly 2% and 7%, respectively. In addition, we further tested our method on the well-known 3D rigid shape dataset ModelNet, and the experimental results demonstrate that our method is also effective for 3D rigid shape retrieval. We also combine the proposed HPF shape features with deep convolutional features for the 3D rigid shape retrieval task, achieving a retrieval performance comparable to the prior state-of-the-art methods, which indicates a strong complementarity between HPF shape features and deep convolutional features.

Visual tracking is a fundamental task in computer vision with significant practical applications in various domains, including surveillance, security, robotics, and human-computer interaction. However, it may face limitations in visible light data, such as low-light environments, occlusion, and camouflage, which can significantly reduce its accuracy. To cope with these challenges, researchers have explored the potential of combining the visible and infrared modalities to improve tracking performance. By leveraging the complementary strengths of visible and infrared data, RGB-infrared fusion tracking has emerged as a promising approach to address these limitations and improve tracking accuracy in challenging scenarios. In this article, we present a review on RGB-infrared fusion tracking. Specifically, we categorize existing RGBT tracking methods into four categories based on their underlying architectures, feature representations, and fusion strategies, namely feature decoupling based method, feature selecting based method, collaborative graph tracking method, and traditional fusion method. Furthermore, we provide a critical analysis of their strengths, limitations, representative methods, and future research directions. To further demonstrate the advantages and disadvantages of these methods, we present a review of publicly available RGBT tracking datasets and analyze the main results on public datasets. Moreover, we discuss some limitations in RGBT tracking at present and provide some opportunities and future directions for RGBT visual tracking, such as dataset diversity, unsupervised and weakly supervised applications. In conclusion, our survey aims to serve as a useful resource for researchers and practitioners interested in the emerging field of RGBT tracking, and to promote further progress and innovation in this area.

Although deep learning techniques have achieved extraordinary accuracy in recognizing human faces, the pose variances of images captured in real-world scenarios still hinder reliable model appliance. To mitigate this gap, we propose to recognize faces via generation frontal face images with a 3D -Guided Deep P ose- I nvariant Face Recognition M odel (3D-PIM) consisted of a simulator and a refiner module. The simulator employs a 3D Morphable Model (3D MM) to fit the shape and appearance features and recover primary frontal images with less training data. The refiner further enhances the image realism on both global facial structure and local details with adversarial training, while keeping the discriminative identity information consistent with original images. An Adaptive Weighting (AW) metric is then adopted to leverage the complimentary information from recovered frontal faces and original profile faces and to obtain credible similarity scores for recognition. Extended experiments verify the superiority of the proposed “recognition via generation” framework over state-of-the-art.

Summary The value of image retrieval has become more and more prominent in the era of big data. However, large numbers of images are missed from current method since the image retrieval precision largely depends on the high quality of images. By common methodology, when the quality of images decreases a little, the accuracy of retrieval would decrease significantly. In particular, it is difficult to retrieve noisy images effectively by conventional approach. Yet large number of the noisy images could not be ignored at the age of data explosion. Aiming at the problem above, we proposed noisy image retrieval model based on field of experts (FoE) optimization. High‐quality learning images could be selected by sparse coding, which is based on similarity calculation model, and the multioption filter combination model enhances the power of FoE model. We set up a database containing a large numbers of noisy images. Over this database, adequate groups of experiments are conducted. The verification of the method concluded its effectiveness and superiority.

Given only the collected hyperspectral data, unmixing aims at obtaining the latent constituent materials and their corresponding fractional abundances. Recently, manynonnegative matrix factorization(NMF)-based algorithms have been developed to deal with this issue. Considering that the abundances of most materials may be sparse, the sparseness constraint is intuitively introduced into NMF. Although sparse NMF algorithms have achieved advanced performance in unmixing, the result is still susceptible to unstable decomposition and noise corruption. To reduce the aforementioned drawbacks, the structural information of the data is exploited to guide the unmixing. Since similar pixel spectra often imply similar substance constructions, clustering can explicitly characterize this similarity. Through maintaining the structural information during the unmixing, the resulting fractional abundances by the proposed algorithm can well coincide with the real distributions of constituent materials. Moreover, the additional clustering-based regularization term also lessens the interference of noise to some extent. The experimental results on synthetic and real hyperspectral data both illustrate the superiority of the proposed method compared with other state-of-the-art algorithms.

Hyperspectral unmixing is one of the most important techniques in analyzing hyperspectral images, which decomposes a mixed pixel into a collection of constituent materials weighted by their proportions. Recently, many sparse nonnegative matrix factorization (NMF) algorithms have achieved advanced performance for hyperspectral unmixing because they overcome the difficulty of absence of pure pixels and sufficiently utilize the sparse characteristic of the data. However, most existing sparse NMF algorithms for hyperspectral unmixing only consider the Euclidean structure of the hyperspectral data space. In fact, hyperspectral data are more likely to lie on a low-dimensional submanifold embedded in the high-dimensional ambient space. Thus, it is necessary to consider the intrinsic manifold structure for hyperspectral unmixing. In order to exploit the latent manifold structure of the data during the decomposition, manifold regularization is incorporated into sparsity-constrained NMF for unmixing in this paper. Since the additional manifold regularization term can keep the close link between the original image and the material abundance maps, the proposed approach leads to a more desired unmixing performance. The experimental results on synthetic and real hyperspectral data both illustrate the superiority of the proposed method compared with other state-of-the-art approaches.