Abstract visual reasoning is a critical benchmark for assessing the cognitive and interpretativecapabilities of artificial intelligence (AI) in computer vision, with broad implications for advancedvisual processing and display-related intelligent perception tasks.Abstract visual reasoning is a criticalbenchmark for assessing the cognitive and interpretative capabilities of artificial intelligence (AI) incomputer vision, with broad implications for advanced visual processing. In this paper, we proposea Hierarchical Attention Network with Slot-weighted Modeling (HASM), a novel visual reasoningframework integrating hierarchical structure modeling and channel-wise feature recalibration, to boostperformance on Raven’s Progressive Matrices (RPM) tasks. The framework comprises two mainmodules: (1) Hierarchical Attention Modeling, which organizes image matrices in a row-first orderto explicitly capture structural dependencies between elements; and (2) Slot-weighted Modeling,which utilizes multi-branch one-dimensional (1D) convolutions to emphasize salient features alongthe channel dimension. Extensive experiments on the I-RAVEN dataset demonstrate that the proposedHASM model achieves an average accuracy of 96.7%, outperforming state-of-the-art (SOTA) modelsacross multiple structural configurations. On the PGM dataset (another widely used RPM benchmark),the model further achieves 98.5% accuracy. These findings validate that the proposed method providesa structure-aware and feature-sensitive solution for abstract visual reasoning tasks, and it holdspromising theoretical value and practical implications for advancing AI-driven visual reasoning inrelated fields.

As a basic quantum algorithm, the Bernstein-Vazirani algorithm is based on the principles of superposition in quantum mechanics, demonstrating superior efficiency over classical computation in finding hidden strings. Due to the high complexity of quantum mechanics, the correctness of quantum algorithms is difficult to guarantee through traditional simulation methods. By contrast, the Bernstein-Vazirani algorithm’s fundamental concepts and mathematical structures can be formalized into logical expressions and verified by higher-order logical reasoning. In this paper, we formally model and verify the Bernstein-Vazirani algorithm in the HOL Light theorem prover. Meanwhile, to indicate the practical significance of our work, we analyze two realistic scenarios, the error correction in quantum key distribution and image encryption and decryption.

Recent studies have shown that video action recognition models are also vulnerable to fooling by adversarial samples. However, currently existing video attack methods usually require high computational overhead (e.g., they generate adversarial perturbations for all frames by default), and most of them are difficult to implement printable attacks in the physical world. To address the above issues, we devise a novel efficient and effective framework for video action recognition attack: Bullet-Screen-Emoji Attack with Temporal Difference Noise (BSE), a reinforcement learning-based black-box attack method that fools the model by simply generating adversarial bullet screens for key frame and scrolling them on clean video. The agent is optimized to make the optimal actions, i.e., searching key frame. Moreover, we introduce a simple and effective temporal difference noise to enhance the attack capability of the adversarial bullet screen and accelerate the convergence speed. Most importantly, BSE enables printable physical attacks. Extensive experiments show that our proposed BSE achieves promising attack performance on mainstream datasets (HMDB51, UCF101 and Kinetics-400) and in the physical world with high efficiency.

Cooperative robots can significantly assist people in their productive activities, improving the quality of their works. Collision detection is vital to ensure the safe and stable operation of cooperative robots in productive activities. As an advanced geometric language, conformal geometric algebra can simplify the construction of the robot collision model and the calculation of collision distance. Compared with the formal method based on conformal geometric algebra, the traditional method may have some defects which are difficult to find in the modelling and calculation. We use the formal method based on conformal geometric algebra to study the collision detection problem of cooperative robots. This paper builds formal models of geometric primitives and the robot body based on the conformal geometric algebra library in HOL Light. We analyse the shortest distance between geometric primitives and prove their collision determination conditions. Based on the above contents, we construct a formal verification framework for the robot collision detection method. By the end of this paper, we apply the proposed framework to collision detection between two single-arm industrial cooperative robots. The flexibility and reliability of the proposed framework are verified by constructing a general collision model and a special collision model for two single-arm industrial cooperative robots.

Influence maximization (IM) aims to identify $k$ vertices that maximize influence spread across a network. While well-studied in regular graphs, IM in hypergraphs presents unique challenges: conventional graph-based IM methods fail to capture hypergraph-specific structural properties, and existing hypergraph IM algorithms lack theoretical guarantees for time complexity and approximation quality. We address these gaps with HyperIM, a novel algorithm leveraging stratified sampling to generate random reversible reachable sets for efficient seed selection. Our key innovation lies in dual-perspective stratified sampling: assigning sampling probabilities based on vertex structural properties while applying size-adaptive sampling strategies. This approach optimizes seed selection, reduces computational costs, and provides rigorous theoretical guarantees. We further propose HyperIM_BRR, which optimizes the required number of reversible reachable sets, achieving substantial cost reduction without sacrificing accuracy. Extensive experiments on real-world hypergraphs demonstrate that our algorithms significantly outperform state-of-the-art methods, delivering faster execution times and superior influence spread.

Adversarial attacks have been extensively studied in the image field. In recent years, research has shown that video recognition models are also vulnerable to adversarial examples. However, most studies about adversarial attacks for video models have focused on perturbation-based methods, while patch-based black-box attacks have received less attention. Despite the excellent performance of perturbationbased attacks, these attacks are impractical for real-world implementation. Most existing patch-based black-box attacks require occluding larger areas and performing more queries to the target model. In this paper, we propose a hardsample style guided patch attack with reinforcement learning (RL) enhanced motion patterns for video recognition (HSPA). Specifically, we utilize the style features of video hard samples and transfer their multi-dimensional style features to images to obtain a texture patch set. Then we use reinforcement learning to locate the patch coordinates and obtain a specific adversarial motion pattern of the patch to successfully perform an effective attack on a video recognition model in both the spatial and temporal dimensions. Our experiments on three widely-used video action recognition models (C3D, LRCN, and TDN) and two mainstream datasets (UCF-101 and HMDB-51) demonstrate the superior performance of our method compared to other state-of-the-art approaches.

Visible-infrared person re-identification (VI-ReID) is a critical cross-modality fine-grained classification task with significant implications for public safety and security applications. Existing VI-ReID methods primarily focus on extracting modality-invariant features for person retrieval. However, due to the inherent lack of texture information in infrared images, these modality-invariant features tend to emphasize global contexts. Consequently, individuals with similar silhouettes are often misidentified, posing potential risks to security systems and forensic investigations. To address this problem, this paper innovatively introduces natural language descriptions to learn the global-local contexts for VI-ReID. Specifically, we design a framework that jointly optimizes visible-infrared alignment plus (VIAP) and visual-textual reasoning (VTR), and introduces local-global joint measure (LJM) to enhance the metric, while proposing a human-LLM collaborative approach to incorporate textual descriptions into existing cross-modal person re-identification datasets. VIAP achieves cross-modal alignment between RGB and IR. It can explicitly utilize designed frequency-aware modality alignment and relationship-reinforced fusion to explore the potential of local cues in global features and modality-invariant information. VTR proposes pooling selection and dual-level reasoning mechanisms to force the image encoder to pay attention to significant regions based on textual descriptions. LJM proposes introducing local feature distances into the measure stage metric to enhance the relevance of matching using fine-grained information. Extensive experimental results on the popular SYSU-MM01 and RegDB datasets show that the proposed method significantly outperforms state-of-the-art approaches. The dataset is publicly available at https://github.com/qyx596/vireid-caption.

ARM TrustZone technology is widely used to provide Trusted Execution Environments (TEEs) for sensitive applications. However, most TEE OSes are implemented as monolithic kernels. In such designs, all components run in the kernel which will lead to a big trusted computing base (TCB). It is difficult to guarantee that all components of the kernel have no security vulnerabilities. The functions of trusted computing, such as integrity measurement and data sealing, will provide further security guarantees. This paper presents MicroTEE, a TEE OS with rich trusted computing primitives based on the microkernel architecture. In MicroTEE, the microkernel provides strong isolation for services and applications. The kernel is only responsible for providing core services such as address space management, thread management, and inter-process communication. Other fundamental services, such as Trusted Service, are implemented as applications at the user layer. Trusted computing primitives provide some security features for trusted applications (TAs), including integrity measurement, data sealing, and remote attestation. Our design avoids the compromise of the whole TEE OS if some kernel service is vulnerable. A monitor has also been added to perform the switch between the secure world and the normal world. Finally, we implemented a MicroTEE prototype on the Freescale i.MX6Q Sabre Lite development board and tested its performance. Evaluation results show that MicroTEE only introduces some necessary and acceptable overhead.

Recent research has shown that deep learning networks are vulnerable to adversarial samples. Although there has been great progress in the study of adversarial attacks on images, there is relatively little research on adversarial attacks in the video domain, especially on intrinsic factors of videos, such as motion blur. In this paper, we devise a novel Grad-Weighted based One-step Motion Blur Attack (GWO-MBA) and a Discrete-Fusion based Progressive Motion Blur Attack (DFP-MBA) for video recognition, starting from the idea of integrating global adversarial attacks and adversarial patch attacks. Concretely, we use gradient maps to filter and weighted fusion motion blur (termed GWO-MBA) to achieve the attack that matches the motion information in the context of the video. In order to make the generated motion blur attack perturbations more natural and improve the attack success rate, we further introduce a progressive decomposition motion blur strategy (termed DFP-MBA) to progressively fuse more realistic discrete motion blurs. Besides, we propose an Aggressive Motion Blur Generation (AMBG), which generates natural motion blur based on the video context and has a better attack effect. The extensive experiments, on the HMDB-51 and UCF-101 datasets, demonstrate the effectiveness and superiority of our proposed attack method. In addition, the attack effectiveness of the mainstream denoising defense model and the deblur model further validates the robustness of our attack method.

Non-prehensile manipulation plays a crucial role in the field of robotics, especially when objects are irregular, cumbersome or heavy. Traditional approaches are usually implemented based on reinforcement learning or imitation learning. However, reinforcement learning methods suffer from the low sampling efficiency with the environment, while imitation learning based ones rely on the time-consuming demonstrations collection. To this end, this paper proposes a novel Causal Policy Learning scheme from Self-play (CaPLS) for pushing manipulation. On one hand, CaPLS provides a light-weight way that the causal prior is learnt from the random self-play data and encoded as a structural causal model (SCM) using a graph neural network (GNN). On the other hand, SCM is used to guide the policy learning combining imitation learning and reinforcement learning. The demonstrations for imitation learning are collected using SCM directly, resulting in initially optimized policy. The reinforcement learning is then implemented to refine the policy for a specific task. It greatly reduces the iteration of interactions in this manner. Experimental results demonstrate that the proposed method can outperform the SOTA methods, and the generalization capability is improved as well. Code will be made publicly available.

Action recognition is a promising task of identifying human activities in videos or images. Human movement is often accompanied by occlusion and blurring, resulting in many approximate behaviors that cannot be correctly recognized. Most methods directly employ local or motion cues to improve global features. Due to insufficient exploration of 3-D depth information, similar actions from the 2-D perspective still cannot be particularity distinguished. To tackle this challenge, this article proposes a novel action recognition approach termed RPS-Net, integrating 3-D human body reconstruction and hybrid pose self-supervision (HPSS). The designed 3-D reconstruction network is named CFFormer, which leveraging a context-fusion structure to generate 3-D meshes as auxiliary input. Among them, the mesh rotated 90 degrees (M9) is exploited to provide multiperspective associative information, which employing spatial residual learning to enhance extra 3-D cues under various interpose variations. Meanwhile, the original images and meshes from the same perspective will perform HPSS with temporal encoding. It is responsible for capturing subtle differences in key point positions and structures across multiple dimensions. Extensive experiments demonstrate that our proposed method significantly surpasses most existing algorithms. And the Top-1 recognition accuracy on SSV2, HMDB51, and Olympic Sports datasets can reach 73.4%, 87.7%, and 96.2%, respectively.

Operating systems are the key foundational components of the software stacks employed in many safety-critical scenarios.A tiny error or loophole in the operating system may cause major failures of the overall software system,resulting in huge economic losses or endangering human lives.Thus,the correctness of the operating system should be verified to reduce the number of such accidents.Traditional testing methods cannot guarantee the exhaustive detection of potential errors in the target system.Therefore,it is necessary to adopt formal methods based on strict mathematical theories for verifying operating systems.In an operating system,mutexes are utilized to coordinate the access of shared resources by tasks and they are a typical means of task synchronization.The functional correctness of mutexes is the key to the correct functioning of multi-task applications.Based on the theorem proof method,this study conducts formal verification on the code of the mutex module of a preemptive microkernel in an interactive theorem prover Coq,gives the formal specifications of the interface functions of this module,and formally proves the functional correctness of these interface functions.

An OS microkernel can be extended by implementing services upon it. A service could introduce an object that references a kernel object, and implement a group of functions that invokes the functions for manipulating the kernel object. We consider the scenario where the microkernel has been verified with machine-checkable proofs, while the services remain to be verified. Moreover, the verification of the microkernel is not performed with the verification of subsequent extension in mind. We address the problem of how to build sufficiently on the verification results for the microkernel, in achieving the verification of the services. Our methodology consists of enhancements to the verification framework for the microkernel, and the design of invariants for establishing the connection between the service-level objects and the kernel-level objects. Using the methodology, we have conducted a substantial formal verification of a group of services extending the inter-task communication functionalities of the preemptive microkernel μ C / OS-II . Our verification uncovers dormant bugs and provides a level of correctness assurance for the services that is above what is achievable through extensive testing.

AbstractPerson/vehicle re‐identification aims to use technologies such as cross‐camera retrieval to associate the same person (same vehicle) in the surveillance videos at different locations, different times, and images captured by different cameras so as to achieve cross‐surveillance image matching, person retrieval and trajectory tracking. It plays an extremely important role in the fields of intelligent security, criminal investigation etc. In recent years, the rapid development of deep learning technology has significantly propelled the advancement of re‐identification (Re‐ID) technology. An increasing number of technical methods have emerged, aiming to enhance Re‐ID performance. This paper summarises four popular research areas in the current field of re‐identification, focusing on the current research hotspots. These areas include the multi‐task learning domain, the generalisation learning domain, the cross‐modality domain, and the optimisation learning domain. Specifically, the paper analyses various challenges faced within these domains and elaborates on different deep learning frameworks and networks that address these challenges. A comparative analysis of re‐identification tasks from various classification perspectives is provided, introducing mainstream research directions and current achievements. Finally, insights into future development trends are presented.

In recent years, video action recognition, as a fundamental task in the field of video understanding, has been deeply explored by numerous researchers.Most traditional video action recognition methods typically involve converting videos into three-dimensional data that encapsulates both spatial and temporal information, subsequently leveraging prevalent image understanding models to model and analyze these data. However,these methods have significant drawbacks. Firstly, when delving into video action recognition tasks, image understanding models often need to be adapted accordingly in terms of model architecture and preprocessing for these spatiotemporal tasks; Secondly, dealing with high-dimensional data often poses greater challenges and incurs higher time costs compared to its lower-dimensional counterparts.To bridge the gap between image-understanding and video-understanding tasks while simplifying the complexity of video comprehension, we introduce a novel video representation architecture, Flatten, which serves as a plug-and-play module that can be seamlessly integrated into any image-understanding network for efficient and effective 3D temporal data modeling.Specifically, by applying specific flattening operations (e.g., row-major transform), 3D spatiotemporal data is transformed into 2D spatial information, and then ordinary image understanding models are used to capture temporal dynamic and spatial semantic information, which in turn accomplishes effective and efficient video action recognition. Extensive experiments on commonly used datasets (Kinetics-400, Something-Something v2, and HMDB-51) and three classical image classification models (Uniformer, SwinV2, and ResNet), have demonstrated that embedding Flatten provides a significant performance improvements over original model.

The huge amount of graph data necessitates sampling methods to support graph-based analysis applications. Node influence is to count the influential nodes with a given node in large graphs that has wide applications including product promotion and information diffusion in social networks. However, existing sampling methods mainly consider node degree to compute the node influence while ignoring the important connections in terms of groups in which nodes participate, resulting in inaccuracy of influence estimations. To this end, this paper proposes group sampling, called GVRW, to count the groups along with node degrees to evaluate node influence in large graphs. Specifically, GVRW changes the way of random walker traversing a large graph from one node to a random neighbor node of the groups to enlarge the sampling space for the sake of characterizing the nodes and groups simultaneously. Furthermore, we carefully design the corresponding estimated method to employ the samples to estimate the specific distributions of groups and node degrees to compute the node influence. Experimental results on real-world graph datasets show that our proposed sampling and estimating methods can accurately obtain the properties and approximate the node influences closer to the real values than existing methods.

Deep neural networks (DNNs) have demonstrated excellent performance across various domains. However, recent studies have shown that deep neural networks are vulnerable to adversarial examples, including DNN-based video action recognition models. While much of the existing research on adversarial attacks against video models focuses on perturbation-based attacks, there is limited research on patch-based black-box attacks. Existing patch-based attack algorithms suffer from the problem of a large search space of optimization algorithms and use patches with simple content, leading to suboptimal attack performance or requiring a large number of queries. To address these challenges, we propose the "Diffusion Patch Attack (DPA) with Spatial-Temporal Cross-Evolution (STCE) for Video Recognition," a novel approach that integrates the excellent properties of the diffusion model into video black-box adversarial attacks for the first time. This integration significantly narrows the parameter search space while enhancing the adversarial content of patches. Moreover, we introduce the spatial-temporal cross-evolutionary algorithm to adapt to the narrowed search space. Specifically, we separate the spatial and temporal parameters and then employ an alternate evolutionary strategy for each parameter type. Extensive experiments conducted on three widely used video action recognition models (C3D, NL, and TPN) and two benchmark datasets (UCF-101 and HMDB-51) demonstrate the superior performance of our approach compared to other state-of-the-art black-box patch attack algorithms.

This paper focuses on weakly supervised temporal action localization, a critical issue within the field of Artificial Intelligence (AI) in the context of the Internet of Things (IoT). The objective is to identify and locate action segments within untrimmed videos, which are solely trained using video-level action labels. Current visual perception and analysis techniques in the IoT face substantial challenges, including a significant amount of noise in videos, the complexity of backgrounds, and the absence of clear motion boundaries in lengthy video sequences. In this paper, we fully recognize that each frame space contains a wealth of information that contributes to classification and localization tasks. Therefore, we propose a method based on modeling features using spatial information within long video frames, aiming to more accurately locate action boundaries and achieve perception of complex data within IoT environments. Additionally, we employ traditional features within our model to alleviate noise issues typically encountered in lengthy videos. Traditional and deep features are processed separately, constituting a two-stream network within the entire model. We conducted comprehensive experiments on the widely used THUMOS14 dataset, demonstrating significant improvements compared to state-of-the-art methods. Furthermore, we conducted experiments on the ActivityNet v1.2 dataset, where traditional features were omitted. The experiments revealed that even without traditional features, our module and two-stream network strategy remained effective within IoT environments.

In SSD-SMR hybrid storage systems, the Persistent Cache (PC) cleaning process in Shingled Magnetic Recording (SMR) disks involves frequent Read-Modify-Write (RMW) operations, significantly increasing system tail latency. Although traditional Q-learning methods alleviate this issue to some extent, the expansion of state space results in an increase in the dimensions of the Q-Table, leading to significant rises in computational and storage costs, thus limiting its ability to handle complex problems. In this paper, we propose an intelligent data prediction management strategy named Augur, based on Deep Reinforcement Learning (DRL), that predicts nodes where high latency is imminent and directs the agent named Pythia to timely redirect the flow of suspect data, effectively reducing RMW operations in SMR. We implement our technique on a real SSD-SMR hybrid storage system. Experimental results show that, compared to Q-learning and Skylight, our method reduces the system tail latency at the 99.9th percentile by 23.61% and 58.35%, and reduces average request latency by 22.54% and 47.56%, respectively.