In density functional theory, the SCAN (Strongly Constrained and Appropriately Normed) and r2SCAN functionals significantly improve over generalized gradient approximation functionals such as PBE (Perdew-Burke-Ernzerhof) in predicting electronic, magnetic, and structural properties across various materials, including transition-metal compounds. However, there remain puzzling cases where SCAN and r2SCAN underperform, such as in calculating the band structure of graphene, the magnetic moment of Fe, the potential energy curve of the Cr2 molecule, and the bond length of VO2. This research identifies a common characteristic among these challenging materials: non-compact covalent bonding through s-s, p-p, or d-d electron hybridization. While SCAN and r2SCAN excel at capturing electron localization at local atomic sites, they struggle to accurately describe electron localization in non-compact covalent bonds, resulting in a biased improvement. To address this issue, we propose the r2SCAN+V approach as a practical modification that improves accuracy across all the tested materials. The parameter V is 4 eV for metallic Fe, but substantially lower for the other cases. Our findings provide valuable insights for the future development of advanced functionals.

Automatic crack detection and segmentation play a significant role in the whole system of unmanned aerial vehicle inspections. In this paper, we have implemented a deep learning framework for crack detection based on classical network architectures including Alexnet, VGG, and Resnet. Moreover, inspired by the feature pyramid network architecture, a hierarchical convolutional neural network (CNN) deep learning framework which is efficient in crack segmentation is also proposed, and its performance of it is compared with other state-of-the-art network architecture. We have summarized the existing crack detection and segmentation datasets and established the largest existing benchmark dataset on the internet for crack detection and segmentation, which is open-sourced for the research community. Our feature pyramid crack segmentation network is tested on the benchmark dataset and gives satisfactory segmentation results. A framework for automatic unmanned aerial vehicle inspections is also proposed and will be established for the crack inspection tasks of various concrete structures. All our self-established datasets and codes are open-sourced at: this https URL

The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particularly model inversion (MI) attacks, posing a significant threat to the privacy and integrity of personal data. The increasing prevalence of these attacks in applications such as biometrics, healthcare, and finance has created an urgent need to understand their mechanisms, impacts, and defense methods. This survey aims to fill the gap in the literature by providing a structured and in-depth review of MI attacks and defense strategies. Our contributions include a systematic taxonomy of MI attacks, extensive research on attack techniques and defense mechanisms, and a discussion about the challenges and future research directions in this evolving field. By exploring the technical and ethical implications of MI attacks, this survey aims to offer insights into the impact of AI-powered systems on privacy, security, and trust. In conjunction with this survey, we have developed a comprehensive repository to support research on MI attacks and defenses. The repository includes state-of-the-art research papers, datasets, evaluation metrics, and other resources to meet the needs of both novice and experienced researchers interested in MI attacks and defenses, as well as the broader field of AI security and privacy. The repository will be continuously maintained to ensure its relevance and utility. It is accessible at this https URL

We present the first comprehensive video polyp segmentation (VPS) study in the deep learning era. Over the years, developments in VPS are not moving forward with ease due to the lack of large-scale fine-grained segmentation annotations. To address this issue, we first introduce a high-quality frame-by-frame annotated VPS dataset, named SUN-SEG, which contains 158,690 colonoscopy frames from the well-known SUN-database. We provide additional annotations with diverse types, i.e., attribute, object mask, boundary, scribble, and polygon. Second, we design a simple but efficient baseline, dubbed PNS+, consisting of a global encoder, a local encoder, and normalized self-attention (NS) blocks. The global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations, which are then progressively updated by two NS blocks. Extensive experiments show that PNS+ achieves the best performance and real-time inference speed (170fps), making it a promising solution for the VPS task. Third, we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based comparisons. Finally, we discuss several open issues and suggest possible research directions for the VPS community.

Depression represents a global mental health challenge requiring efficient and reliable automated detection methods. Current Transformer- or Graph Neural Networks (GNNs)-based multimodal depression detection methods face significant challenges in modeling individual differences and cross-modal temporal dependencies across diverse behavioral contexts. Therefore, we propose P$^3$HF (Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network) with three key innovations: (1) personality-guided representation learning using LLMs to transform discrete individual features into contextual descriptions for personalized encoding; (2) Hypergraph-Former architecture modeling high-order cross-modal temporal relationships; (3) event-level domain disentanglement with contrastive learning for improved generalization across behavioral contexts. Experiments on MPDD-Young dataset show P$^3$HF achieves around 10\% improvement on accuracy and weighted F1 for binary and ternary depression classification task over existing methods. Extensive ablation studies validate the independent contribution of each architectural component, confirming that personality-guided representation learning and high-order hypergraph reasoning are both essential for generating robust, individual-aware depression-related representations. The code is released at this https URL.

In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the integration between weak-to-strong consistency regularization and network perturbation has been relatively rare. We note several problems with existing network perturbations in SSS that may contribute to this phenomenon. By revisiting network perturbations, we introduce a new approach for network perturbation to expand the existing weak-to-strong consistency regularization for unlabeled data. Additionally, we present a volatile learning process for labeled data, which is uncommon in existing research. Building upon previous work that includes input-level and feature-level perturbations, we present MLPMatch (Multi-Level-Perturbation Match), an easy-to-implement and efficient framework for semi-supervised semantic segmentation. MLPMatch has been validated on the Pascal VOC and Cityscapes datasets, achieving state-of-the-art performance. Code is available from this https URL.

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method.

Existing DNS configuration verification tools face significant issues (e.g., inefficient and lacking support for incremental verification). Inspired by the advancements in recent work of distributed data plane verification and the resemblance be- tween the data plane and DNS configuration, we tackle the challenge of DNS misconfiguration by introducing Janus, a DNS verification tool. Our key insight is that the process of a nameserver handling queries can be transformed into a matching process on a match-action table. With this insight, Janus consists of (1) an efficient data structure for partition query space based on the behaviors, (2) a symbolic execution algorithm that specifies how a single nameserver can efficiently cover all possible queries and ensure the accuracy of verification, (3) a mechanism to support incremental verification with less computational effort. Extensive experiments on real-world datasets (with over 6 million resource records) show that Janus achieves significant speedups, with peak improvements of up to 255.7x and a maximum 6046x reduction in the number of LECs.

We report a measurement of the cross section for the process $e^+e^-\to\pi^+\pi^-J/\psi$ around the $X(3872)$ mass in search for the direct formation of $e^+e^-\to X(3872)$ through the two-photon fusion process. No enhancement of the cross section is observed at the $X(3872)$ peak and an upper limit on the product of electronic width and branching fraction of $X(3872)\to\pi^+\pi^-J/\psi$ is determined to be \Gamma_{ee}\times\mathcal{B}(X(3872)\to\pi^+\pi^-J/\psi)<7.5\times10^{-3}\,\text{eV} at $90\,\%$ confidence level under an assumption of total width of $1.19\pm0.21$ MeV. This is an improvement of a factor of about $17$ compared to the previous limit. Furthermore, using the latest result of $\mathcal{B}(X(3872)\to\pi^+\pi^-J/\psi)$, an upper limit on the electronic width $\Gamma_{ee}$ of $X(3872)$ is obtained to be <0.32\,\text{eV} at the $90\,\%$ confidence level.

We study unwrapped two-point functions for the Ising model, the self-avoiding walk and a random-length loop-erased random walk on high-dimensional lattices with periodic boundary conditions. While the standard two-point functions of these models have been observed to display an anomalous plateau behaviour, the unwrapped two-point functions are shown to display standard mean-field behaviour. Moreover, we argue that the asymptotic behaviour of these unwrapped two-point functions on the torus can be understood in terms of the standard two-point function of a random-length random walk model on Zd. A precise description is derived for the asymptotic behaviour of the latter. Finally, we consider a natural notion of the Ising walk length, and show numerically that the Ising and SAW walk lengths on high-dimensional tori show the same universal behaviour known for the SAW walk length on the complete graph.

Multimodal pathological images are usually in clinical diagnosis, but computer vision-based multimodal image-assisted diagnosis faces challenges with modality fusion, especially in the absence of expert-annotated data. To achieve the modality fusion in multimodal images with label scarcity, we propose a novel ``pretraining + fine-tuning" framework for multimodal semi-supervised medical image classification. Specifically, we propose a synergistic learning pretraining framework of consistency, reconstructive, and aligned learning. By treating one modality as an augmented sample of another modality, we implement a self-supervised learning pre-train, enhancing the baseline model's feature representation capability. Then, we design a fine-tuning method for multimodal fusion. During the fine-tuning stage, we set different encoders to extract features from the original modalities and provide a multimodal fusion encoder for fusion modality. In addition, we propose a distribution shift method for multimodal fusion features, which alleviates the prediction uncertainty and overfitting risks caused by the lack of labeled samples. We conduct extensive experiments on the publicly available gastroscopy image datasets Kvasir and Kvasirv2. Quantitative and qualitative results demonstrate that the proposed method outperforms the current state-of-the-art classification methods. The code will be released at: this https URL.

Lateral predictive coding is a recurrent neural network which creates energy-efficient internal representations by exploiting statistical regularity in sensory inputs. Here we investigate the trade-off between information robustness and energy in a linear model of lateral predictive coding analytically and by numerical minimization of a free energy. We observe several phase transitions in the synaptic weight matrix, especially a continuous transition which breaks reciprocity and permutation symmetry and builds cyclic dominance and a discontinuous transition with the associated sudden emergence of tight balance between excitatory and inhibitory interactions. The optimal network follows an ideal-gas law in an extended temperature range and saturates the efficiency upper-bound of energy utilization. These results bring theoretical insights on the emergence and evolution of complex internal models in predictive processing systems.

We address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects. Specifically, our method integrates the intensity and depth information at multiple levels of spatial granularity. Firstly, a scene-level deep network produces an initial coarse segmentation, based on which we select a few potential object regions to zoom in and perform fine segmentation. The results of the above steps are further integrated into a densely connected conditional random field that learns to respect the appearance, depth, and spatial affinities with pixel-level accuracy. In addition, we create a new RGBD waste object segmentation dataset, MJU-Waste, that is made public to facilitate future research in this area. The efficacy of our method is validated on both MJU-Waste and the Trash Annotation in Context (TACO) dataset.

We present a novel facial expression recognition network, called Distract your Attention Network (DAN). Our method is based on two key observations. Firstly, multiple classes share inherently similar underlying facial appearance, and their differences could be subtle. Secondly, facial expressions exhibit themselves through multiple facial regions simultaneously, and the recognition requires a holistic approach by encoding high-order interactions among local features. To address these issues, we propose our DAN with three key components: Feature Clustering Network (FCN), Multi-head cross Attention Network (MAN), and Attention Fusion Network (AFN). The FCN extracts robust features by adopting a large-margin learning objective to maximize class separability. In addition, the MAN instantiates a number of attention heads to simultaneously attend to multiple facial areas and build attention maps on these regions. Further, the AFN distracts these attentions to multiple locations before fusing the attention maps to a comprehensive one. Extensive experiments on three public datasets (including AffectNet, RAF-DB, and SFEW 2.0) verified that the proposed method consistently achieves state-of-the-art facial expression recognition performance. Code will be made available at this https URL

Transition-metal compounds (TMCs) with open-shell d-electrons are characterized by a complex interplay of lattice, charge, orbital, and spin degrees of freedom, giving rise to a diverse range of fascinating applications. Often exhibiting exotic properties, these compounds are commonly classified as correlated systems due to strong inter-electronic interactions called Hubbard U. This inherent complexity presents significant challenges to Kohn-Sham density functional theory (KS-DFT), the most widely used electronic structure method in condensed matter physics and materials science. While KS-DFT is, in principle, exact for the ground-state total energy, its exchange-correlation energy must be approximated in practice. The mean-field nature of KS implementations, combined with the limitations of current exchange-correlation density functional approximations, has led to the perception that DFT is inadequate for correlated systems, particularly TMCs. Consequently, a common workaround involves augmenting DFT with an on-site Hubbard-like U correction. In recent years, the strongly constrained and appropriately normed (SCAN) density functional, along with its refined variant r2SCAN, has achieved remarkable progress in accurately describing the structural, energetic, electronic, magnetic, and vibrational properties of TMCs, challenging the traditional perception of DFT's limitations. This review explores the design principles of SCAN and r2SCAN, highlights their key advancements in studying TMCs, explains the mechanisms driving these improvements, and addresses the remaining challenges in this evolving field.

Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing. Due to the highly ill-posed issue, additional inputs, typically user-defined trimaps or scribbles, are usually needed to reduce the uncertainty. Although effective, it is either time consuming or only suitable for experienced users who know where to place the strokes. In this work, we propose a decomposed-uncertainty-guided matting (dugMatting) algorithm, which explores the explicitly decomposed uncertainties to efficiently and effectively improve the results. Basing on the characteristic of these uncertainties, the epistemic uncertainty is reduced in the process of guiding interaction (which introduces prior knowledge), while the aleatoric uncertainty is reduced in modeling data distribution (which introduces statistics for both data and possible noise). The proposed matting framework relieves the requirement for users to determine the interaction areas by using simple and efficient labeling. Extensively quantitative and qualitative results validate that the proposed method significantly improves the original matting algorithms in terms of both efficiency and efficacy.

The stability of long-range order against quenched disorder is a central problem in statistical mechanics. This paper develops a generalized framework extending the Ding-Zhuang method and integrated with the Pirogov-Sinai framework, establishing a systematic scheme for studying phase transitions of long-range order in disordered systems. We axiomatize the Ding-Zhuang approach into a theoretical framework consisting of the Peierls condition and a local symmetry condition. For systems in dimensions $d \geq 3$ satisfying these conditions, we prove the persistence of long-range order at low temperatures and under weak disorder, with multiple coexisting distinct Gibbs states. The framework's versatility is demonstrated for diverse models, providing a systematic extension of Peierls methods to disordered systems.

Maximum entropy principle (MEP) offers an effective and unbiased approach to inferring unknown probability distributions when faced with incomplete information, while neural networks provide the flexibility to learn complex distributions from data. This paper proposes a novel neural network architecture, the MEP-Net, which combines the MEP with neural networks to generate probability distributions from moment constraints. We also provide a comprehensive overview of the fundamentals of the maximum entropy principle, its mathematical formulations, and a rigorous justification for its applicability for non-equilibrium systems based on the large deviations principle. Through fruitful numerical experiments, we demonstrate that the MEP-Net can be particularly useful in modeling the evolution of probability distributions in biochemical reaction networks and in generating complex distributions from data.