检索结果-内蒙古大学图书馆

Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liang, Hanzhe Zhou, Jie Chen, Xuanxin Dai, Tao Wang, Jinbao Gao, Can College of Computer Science and Software Engineering Shenzhen University China Shenzhen Audencia Financial Technology Institute Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Faculty of Education Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgements to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Semantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem’s causal logic. Copyright © 2025, The Authors. All rights reserved.

关键词： Fences

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching 39

学校读者我要写书评

暂无评论

DAMPER: A Dual-Stage Medical Report Generation Framework wit...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Diagnosis

Semi-Supervised Clustering Framework for Fine-grained Scene Graph Generation 39

学校读者我要写书评

暂无评论

Semi-Supervised Clustering Framework for Fine-grained Scene ...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yang, Jiarui Wang, Chuan Zhang, Jun Wu, Shuyi Jinjing, Zhao Liu, Zeming Yang, Liang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Institute of Information Engineering CAS China School of Computer Science and Technology Beijing JiaoTong University China Guangdong Provincial Key Lab of Intell. Info. Processing & Shenzhen Key Lab of Media Security Shenzhen University China Information Research Center of Military Science PLA Academy of Military Science China National Key Laboratory of Science and Technology on Information System Security China School of Computer Science and Engineering Beihang University China School of Artificial Intelligence Hebei University of Technology China

ISBN: (纸本)157735897X

Scene Graph Generation (SGG) aims to detect all objects and identify their pairwise relationships existing in the scene. Considering the substantial human labor costs, existing scene graph annotations are often sparse and biased, which result in confusion training with low-frequency predicates. In this work, we design a Semi-Supervised Clustering framework for Scene Graph Generation (SSC-SGG) that uses the sparse labeled data to guide the generation of effective pseudo-labels from unlabeled object pairs, thus enriching the labeled sample space, especially for low-frequency interaction samples. We approach from the perspective of clustering, reducing the problem of confirmation bias in a self-training manner. Specifically, we first enhance the model’s robustness to feature extraction via prototype-based clustering, aggregating different relationship augmented features onto the same prototype. Secondly, we design a dynamic pseudo-label assignment algorithm based on a mini-batch, which adjusts the detection sensitivity to different frequency samples from the historical assignment. Finally, we conduct joint training on the pseudo-labels and the labeled data. We conduct experiments on various SGG models and achieve substantial overall performance improvements, demonstrating the effectiveness of SSC-SGG. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

A posteriori error estimation for an interior penalty virtual element method of Kirchhoff plates

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Feng, Fang Hu, Yuming Yu, Yue Zhao, Jikun School of Mathematics and Statistics Nanjing University of Science and Technology Nanjing China Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education National Center for Applied Mathematics in Hunan School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China School of Mathematics and Statistics Zhengzhou University Zhengzhou450001 China

In this paper, we develop a residual-type a posteriori error estimation for an interior penalty virtual element method (IPVEM) for the Kirchhoff plate bending problem. Building on the work in [18], we adopt a modified discrete variational formulation that incorporates the H1-elliptic projector in the jump and average terms. This allows us to simplify the numerical implementation by including the H1-elliptic projector in the computable error estimators. We derive the reliability and efficiency of the a posteriori error bound by constructing an enriching operator and establishing some related error estimates that align with C0-continuous interior penalty finite element methods. As observed in the a priori analysis, the interior penalty virtual elements exhibit similar behaviors to C0continuous elements despite its discontinuity. This observation extends to the a posteriori estimate since we do not need to account for the jumps of the function itself in the discrete scheme and the error estimators. As an outcome of the error estimator, an adaptive VEM is introduced by means of the mesh refinement strategy with the one-hanging-node rule. Numerical results from several benchmark tests confirm the robustness of the proposed error estimators and show the efficiency of the resulting adaptive VEM. Copyright © 2024, The Authors. All rights reserved.

关键词： Discrete element methods

Attributed Multi-order Graph Convolutional Network for Heterogeneous Graphs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Zhaoliang Wu, Zhihao Zhong, Luying Plant, Claudia Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Faculty of Computer Science University of Vienna Vienna1090 Austria ds:UniVie Vienna1090 Austria

Heterogeneous graph neural networks aim to discover discriminative node embeddings and relations from multi-relational networks. One challenge of heterogeneous graph learning is the design of learnable meta-paths, which significantly influences the quality of learned embeddings. Thus, in this paper, we propose an Attributed Multi-Order Graph Convolutional Network (AMOGCN), which automatically studies meta-paths containing multi-hop neighbors from an adaptive aggregation of multi-order adjacency matrices. The proposed model first builds different orders of adjacency matrices from manually designed node connections. After that, an intact multi-order adjacency matrix is attached from the automatic fusion of various orders of adjacency matrices. This process is supervised by the node semantic information, which is extracted from the node homophily evaluated by attributes. Eventually, we utilize a one-layer simplifying graph convolutional network with the learned multi-order adjacency matrix, which is equivalent to the cross-hop node information propagation with multi-layer graph neural networks. Substantial experiments reveal that AMOGCN gains superior semi-supervised classification performance compared with state-of-the-art competitors. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Existence of Solutions for the Continuous Algebraic Riccati Equation via Polynomial Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Juan Zhao, Wenjie Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China School of Mathematics and Statistics Hunan First Normal University Hunan Changsha410205 China School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

This paper studies the solution existence of the continuous-time algebraic Riccati equation (CARE). We formulate the CARE as two constrained polynomial optimization problems, and then use Lasserre's hierarchy of semi-definite relaxations to solve them. Compared to the existing work, our approaches can obtain the exact positive semi-definite solution of the CARE when the coefficient matrices are symmetric. Moreover, our methods can detect the nonexistence of the positive semi-definite solution for the CARE. Numerical examples show that our approaches are effective compared to the existing methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Riccati equations

Research on Scientific Workflow Scheduling Based on Fuzzy Theory Under Edge Environment 15th

学校读者我要写书评

暂无评论

Research on Scientific Workflow Scheduling Based on Fuzzy Th...

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Lin, Chaowei Lin, Bing Chen, Xing College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Fuzhou350108 China College of Physics and Energy Fujian Normal University Fuzhou350117 China

ISBN: (纸本)9789811625398

With the rapid development of Internet of Everything (IoE) and the popularization of 4G/5G wireless networks, edge computing has gradually become the mainstream. In actual edge environment, some factors have an uncertain impact on scientific workflow scheduling, such as CPU load and bandwidth fluctuations of servers. Aiming at scientific workflow scheduling under uncertain edge environment, based on fuzzy theory, triangular fuzzy numbers (TFNs) were used to represent task computation time and data transmission time. In addition, an Adaptive Discrete Fuzzy GA-based Particle Swarm Optimization (ADFGA-PSO) is proposed to reduce the fuzzy execution cost while satisfying the scientific workflow’s deadline. The uncertainty of workflow scheduling was introduced, which caused by server execution performance fluctuations during task computation and bandwidth fluctuations during data transmission. Meanwhile, two-dimensional discrete particle is adopted to encode the fuzzy scheduling strategy of workflow, and the two-point crossover operator, neighborhood mutation and adaptive multipoint mutation operator of genetic algorithm (GA) were introduced to improve the diversity of population and avoid the local optimum. Experimental results show that compared with other algorithms, ADFGA-PSO can obtain better fuzzy execution cost for deadline-constrained workflow scheduling under uncertain edge environment. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Edge computing

Gaf-Net: Graph Attention Fusion Network for Multi-View Semi-Supervised Classification

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Song, Na Du, Shide Wu, Zhihao Zhong, Luying Wang, Shiping School of Computer Science and Technology Hainan University Hainan570228 China School of Mechanical Electrical and Information Engineering Putian University Putian351100 China College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China

Multi-view semi-supervised classification is a typical task to classify data using a small amount of supervised information, which has attracted a lot of attention from researchers in past years. In practice, existing methods focus more on extracting spatial or spectral features using graph convolutional neural networks without considering the diversity and variability of graph structures and the contributions of different views. To address this challenge, a network framework termed graph attention fusion network is proposed, which is comprised of two phases: view-specific feature embedding and graph embedding fusion. In the former feature extraction stage, view-specific feature embedding module can flexibly focus on the neighborhood calculation operation to learn a weight for each neighboring node. In the latter feature fusion stage, the graph embedding fusion module is performed by complementarity and consistency to fuse these embeddings for semi-supervised classification tasks. We conduct extensive experiments in terms of semi-supervised classification on real-world datasets to validate the superiority of the proposed method over various existing state-ofthe-art methods. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Nonreciprocity with Structured Light Using Optical Pumping in Hot Atoms

学校读者我要写书评

暂无评论

Physical Review Applied 2022年第2期18卷 024027-024027页

作者： Fei Song Zhiping Wang Enze Li Benli Yu Zhixiang Huang Key Laboratory of Opto-Electronic Information Acquisition and Manipulation Ministry of Education Anhui University Hefei 230601 China and Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei 230601 China Key Laboratory of Quantum Information University of Science and Technology of China Hefei Anhui 230026 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei 230039 China

Nonreciprocal transmission of structured light has possible applications in high-capacity optical communication and high-dimensional signal processing. Here, we demonstrate the magnet-free and cavity-free optical nonreciprocity of an orbital-angular-momentum (OAM) beam using optical-pumping technology with the assistance of the Doppler effect in hot atoms. By using optical pumping to induce a direction-dependent population transfer of the ground-state atoms, we realize optical nonreciprocity for the signal laser that is carrying OAM. Interestingly, an isolation ratio close to 30 dB and maximum transmission over 0.86 can be achieved simultaneously without the use of an optical cavity. Due to the unique amplitude and helical phase profile of the structured light, our proposal may open an avenue for exploring the singularity characteristics of optical nonreciprocity using structured light.

关键词： Angular momentum of light Light-matter interaction Non-reciprocal transmission Optical pumping Alkali metals Atomic gases Communication networks Devices