Searcharxiv⌕ Search

arXiv subjects

Yuanyuan Qiao

Publications and source records attributed to Yuanyuan Qiao.

13 recordsLinked to original sources
arXiv2026

No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection

The collection and detection of video anomaly data has long been a challenging problem due to its rare occurrence and spatio-temporal scarcity. Existing video anomaly detection (VAD) methods under perform in open-world scenarios. Key contributing factors include limited dataset diversity, and inadequate understanding of context-dependent anomalous semantics. To address these issues, i) we propose LAVIDA, an end-to-end zero-shot video anomaly detection framework. ii) LAVIDA employs an Anomaly Exposure Sampler that transforms segmented objects into pseudo-anomalies to enhance model adaptability to unseen anomaly categories. It further integrates a Multimodal Large Language Model (MLLM) to bolster semantic comprehension capabilities. Additionally, iii) we design a token compression approach based on reverse attention to handle the spatio-temporal scarcity of anomalous patterns and decrease computational cost. The training process is conducted solely on pseudo anomalies without any VAD data. Evaluations across four benchmark VAD datasets demonstrate that LAVIDA achieves SOTA performance in both frame-level and pixel-level anomaly detection under the zero-shot setting. Our code is available in https://github.com/VitaminCreed/LAVIDA.

cs.CV↗
arXiv2025

Global well-posedness and large-time behavior for three-dimensional magneto-micropolar equations with horizontal dissipation

This paper is concerned with the stability and large-time behavior for 3D magneto-micropolar equations with horizontal dissipation. The global well-posedness of the aforementioned system is established, with the initial data and its vertical derivatives required to be sufficiently small in $L^2$ space. Moreover, we obtain the optimal decay rates for the $H^1$-norm of the solution. The proofs of our main results rely on the special structure of the equations and anisotropic Sobolev-type inequalities.

math.AP↗
arXiv2025

An Automated Attack Investigation Approach Leveraging Threat-Knowledge-Augmented Large Language Models

Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is essential for effective attack investigation, yet existing methods suffer from poor platform generality, limited generalization to evolving tactics, and an inability to produce analyst-ready reports. Large Language Models (LLMs) offer strong semantic understanding and summarization capabilities, but in this domain they struggle to capture the long-range, cross-log dependencies critical for accurate reconstruction. To solve these problems, we present an LLM-empowered attack investigation framework augmented with a dynamically adaptable Kill-Chain-aligned threat knowledge base. We organizes attack-relevant behaviors into stage-aware knowledge units enriched with semantic annotations, enabling the LLM to iteratively retrieve relevant intelligence, perform causal reasoning, and progressively expand the investigation context. This process reconstructs multi-phase attack scenarios and generates coherent, human-readable investigation reports. Evaluated on 15 attack scenarios spanning single-host and multi-host environments across Windows and Linux (over 4.3M log events, 7.2 GB of data), the system achieves an average True Positive Rate (TPR) of 97.1% and an average False Positive Rate (FPR) of 0.2%, significantly outperforming the SOTA method ATLAS, which achieves an average TPR of 79.2% and an average FPR of 29.1%.

cs.CR↗
arXiv2025

Global well-posedness and exponential decay of strong solution for the three-dimensional inhomogeneous incompressible micropolar equations with density-dependent transport coefficients and large initial data

In this paper, we consider the Dirichlet problem of three-dimensional inhomogeneous incompressible micropolar equations with density-dependent viscosity. Under the assumption that the coefficients are power functions of the density, we establish the global existence of strong solutions as long as the initial density is linear equivalent to a large constant state. There is no restriction on the size of initial velocity and micro-rotational velocity. As a by-product, we prove the exponential decay for the solution.

math.AP↗
arXiv2025

DenSe-AdViT: A novel Vision Transformer for Dense SAR Object Detection

Vision Transformer (ViT) has achieved remarkable results in object detection for synthetic aperture radar (SAR) images, owing to its exceptional ability to extract global features. However, it struggles with the extraction of multi-scale local features, leading to limited performance in detecting small targets, especially when they are densely arranged. Therefore, we propose Density-Sensitive Vision Transformer with Adaptive Tokens (DenSe-AdViT) for dense SAR target detection. We design a Density-Aware Module (DAM) as a preliminary component that generates a density tensor based on target distribution. It is guided by a meticulously crafted objective metric, enabling precise and effective capture of the spatial distribution and density of objects. To integrate the multi-scale information enhanced by convolutional neural networks (CNNs) with the global features derived from the Transformer, Density-Enhanced Fusion Module (DEFM) is proposed. It effectively refines attention toward target-survival regions with the assist of density mask and the multiple sources features. Notably, our DenSe-AdViT achieves 79.8% mAP on the RSDD dataset and 92.5% on the SIVED dataset, both of which feature a large number of densely distributed vehicle targets.

cs.CV↗
arXiv2023

Global well-posedness for 2D inviscid and resistive MHD system near an equilibrium

We study the global existence of classical solutions for two-dimensional incompressible MHD system with only magnetic diffusion. By using the time-weighted lower-order energy and uniformly bounded higher-order energy estimates, we prove the global existence result under the assumption that the initial magnetic field is close enough to a constant magnetic vorticity equilibrium.

math.AP↗
arXiv2023

An Adaptive Spatial-Temporal Local Feature Difference Method for Infrared Small-moving Target Detection

Detecting small moving targets accurately in infrared (IR) image sequences is a significant challenge. To address this problem, we propose a novel method called spatial-temporal local feature difference (STLFD) with adaptive background suppression (ABS). Our approach utilizes filters in the spatial and temporal domains and performs pixel-level ABS on the output to enhance the contrast between the target and the background. The proposed method comprises three steps. First, we obtain three temporal frame images based on the current frame image and extract two feature maps using the designed spatial domain and temporal domain filters. Next, we fuse the information of the spatial domain and temporal domain to produce the spatial-temporal feature maps and suppress noise using our pixel-level ABS module. Finally, we obtain the segmented binary map by applying a threshold. Our experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods for infrared small-moving target detection.

cs.CV↗
arXiv2023

Joint Optimization of Resource Allocation and User Association in Multi-Frequency Cellular Networks Assisted by RIS

Due to the development of communication technology and the rise of user network demand, a reasonable resource allocation for wireless networks is the key to guaranteeing regular operation and improving system performance. Various frequency bands exist in the natural network environment, and heterogeneous cellular network (HCN) has become a hot topic for current research. Meanwhile, Reconfigurable Intelligent Surface (RIS) has become a key technology for developing next-generation wireless networks. By modifying the phase of the incident signal arriving at the RIS surface, RIS can improve the signal quality at the receiver and reduce co-channel interference. In this paper, we develop a RIS-assisted HCN model for a multi-base station (BS) multi-frequency network, which includes 4G, 5G, millimeter wave (mmwave), and terahertz networks, and considers the case of multiple network coverage users, which is more in line with the realistic network characteristics and the concept of 6G networks. We propose the optimization objective of maximizing the system sum rate, which is decomposed into two subproblems, i.e., the user resource allocation and the phase shift optimization problem of RIS components. Due to the NP-hard and coupling relationship, we use the block coordinate descent (BCD) method to alternately optimize the local solutions of the coalition game and the local discrete phase search algorithm to obtain the global solution. In contrast, most previous studies have used the coalition game algorithm to solve the resource allocation problem alone. Simulation results show that the algorithm performs better than the rest of the algorithms, effectively improves the system sum rate, and achieves performance close to the optimal solution of the traversal algorithm with low complexity.

cs.IT↗
arXiv2023

Resource Allocation for RIS-Assisted Device-to-Device Communications in Heterogeneous Cellular Networks

In recent years, with the explosive growth of data traffic, communication base stations (BSs) need to serve more and more users. Offloading traffic from BSs has become an efficient way to reduce the burden on BSs. Device-to-Device (D2D) communications have emerged to improve spectrum utilization by reusing the frequency spectrum of the cellular frequency band. In the general environment, Heterogeneous Cellular Networks (HCNs) including millimeter wave (mm-wave) have appeared. Since the D2D link allows to share of spectrum resources with the cellular user, it will bring potential interference to the cellular user. Fortunately, an emerging technology called Reconfigurable Intelligent Surface (RIS) can mitigate the severe interference caused by D2D links by shaping the incident beam and improving the multipath phase shift. In this paper, we study the resource allocation scheme to maximize the system sum rate, in the RISassisted single-cell heterogeneous D2D communication scenario. To solve the Block Coordinate Descent (BCD) problem, the problem of maximizing the sum rate is decomposed into three sub-problems. The resource allocation sub-problem is solved by a coalitional game method based on the game theory. The power allocation problem of the coalition converts the concave function into a convex optimization by mathematical transformation. The problem is solved by the gradient descent method. The local search method is adopted to find the optimum for the phase conversion problem. Then iterate until the difference of sum rate is less than the threshold. The simulation results show that the designed algorithm is superior to other benchmark schemes in the literature.

cs.IT↗
arXiv2023

Deep Reinforcement Learning Based Tracking Control of an Autonomous Surface Vessel in Natural Waters

Accurate control of autonomous marine robots still poses challenges due to the complex dynamics of the environment. In this paper, we propose a Deep Reinforcement Learning (DRL) approach to train a controller for autonomous surface vessel (ASV) trajectory tracking and compare its performance with an advanced nonlinear model predictive controller (NMPC) in real environments. Taking into account environmental disturbances (e.g., wind, waves, and currents), noisy measurements, and non-ideal actuators presented in the physical ASV, several effective reward functions for DRL tracking control policies are carefully designed. The control policies were trained in a simulation environment with diverse tracking trajectories and disturbances. The performance of the DRL controller has been verified and compared with the NMPC in both simulations with model-based environmental disturbances and in natural waters. Simulations show that the DRL controller has 53.33% lower tracking error than that of NMPC. Experimental results further show that, compared to NMPC, the DRL controller has 35.51% lower tracking error, indicating that DRL controllers offer better disturbance rejection in river environments than NMPC.

cs.RO↗
arXiv2023

Survey of Deep Learning for Autonomous Surface Vehicles in the Marine Environment

Within the next several years, there will be a high level of autonomous technology that will be available for widespread use, which will reduce labor costs, increase safety, save energy, enable difficult unmanned tasks in harsh environments, and eliminate human error. Compared to software development for other autonomous vehicles, maritime software development, especially on aging but still functional fleets, is described as being in a very early and emerging phase. This introduces very large challenges and opportunities for researchers and engineers to develop maritime autonomous systems. Recent progress in sensor and communication technology has introduced the use of autonomous surface vehicles (ASVs) in applications such as coastline surveillance, oceanographic observation, multi-vehicle cooperation, and search and rescue missions. Advanced artificial intelligence technology, especially deep learning (DL) methods that conduct nonlinear mapping with self-learning representations, has brought the concept of full autonomy one step closer to reality. This paper surveys the existing work regarding the implementation of DL methods in ASV-related fields. First, the scope of this work is described after reviewing surveys on ASV developments and technologies, which draws attention to the research gap between DL and maritime operations. Then, DL-based navigation, guidance, control (NGC) systems and cooperative operations, are presented. Finally, this survey is completed by highlighting the current challenges and future research directions.

cs.RO↗
arXiv2020

Cross-stained Segmentation from Renal Biopsy Images Using Multi-level Adversarial Learning

Segmentation from renal pathological images is a key step in automatic analyzing the renal histological characteristics. However, the performance of models varies significantly in different types of stained datasets due to the appearance variations. In this paper, we design a robust and flexible model for cross-stained segmentation. It is a novel multi-level deep adversarial network architecture that consists of three sub-networks: (i) a segmentation network; (ii) a pair of multi-level mirrored discriminators for guiding the segmentation network to extract domain-invariant features; (iii) a shape discriminator that is utilized to further identify the output of the segmentation network and the ground truth. Experimental results on glomeruli segmentation from renal biopsy images indicate that our network is able to improve segmentation performance on target type of stained images and use unlabeled data to achieve similar accuracy to labeled data. In addition, this method can be easily applied to other tasks.

eess.IV↗