检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zheng, Yaoyan Yang, Hongyu Huang, Di State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai201112 China Zhejiang Industrial Big Data and Robot Intelligent System Key Laboratory Hangzhou Innovation Institute Beihang University Hangzhou310051 China

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation process, underscore the need for further innovation. In response, we present Deep Common Feature Mining (DCFM), a novel approach strategically designed to address these challenges by leveraging the concept of feature sharing. DCFM explicitly decomposes features into two complementary components. The common representation extracted from a key-frame furnishes essential high-level information to neighboring non-key frames, allowing for direct re-utilization without feature propagation. Simultaneously, the independent feature, derived from each video frame, captures rapidly changing information, providing frame-specific clues crucial for segmentation. To achieve such decomposition, we employ a symmetric training strategy tailored for sparsely annotated data, empowering the backbone to learn a robust high-level representation enriched with common information. Additionally, we incorporate a self-supervised loss function to reinforce intra-class feature similarity and enhance temporal consistency. Experimental evaluations on the VSPW and Cityscapes datasets demonstrate the effectiveness of our method, showing a superior balance between accuracy and efficiency. The implementation is available at https://***/BUAAHugeGun/DCFM. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

arXiv

引用

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

arXiv

引用

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

HRTS: Hierarchical Rauch-Tung-Striebel Smoother With Online Learning Priors for EEG Denoising

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第2期9卷 673-688页

作者： Wang, Chuan-Sheng Zhang, Ling Fu, Tian-Lin Chen, Zhao-Qi Zhang, Fu-Quan Department of Automatic Control Technical Polytechnic University of Catalonia Autonomous Region of Catalonia Barcelona Spain School of Computer and Data Science Minjiang University No.200 Xiyuangong Road Fuzhou University Town Fujian Province Fuzhou City China College of Computer and Big Data Fuzhou University No.2 Wulongjiang North Road Fuzhou University Town Fujian Province Fuzhou City China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Fuzhou Technology Innovation Center of Intelligent Manufacturing Information System Minjiang University No.200 Xiyuangong Road Fuzhou University Town Fujian Province Fuzhou City China Fujian Province University No.1 Campus New Village Longjiang Street Fujian Province Fuqing City China

Electroencephalogram (EEG) is a nonlinear signal that reflects the physio-logical state of the brain at different times, containing rich information. However, the possible interference during the collection and transmission process often leads to a large amount of unnecessary noise in the EEG signal. Traditional denoising methods may face difficulties in high-dimensional data processing and the inability to effectively handle different types of Gaussian white noise. To better eliminate the interference of Gaussian white noise, this article specifically adopts the Hierarchical Rauch-Tung-Striebel Smoother (HRTS) method. This method can effectively integrate the learned structural prior EEG signals into the state space model, thereby describing the relationship between EEG signals and noise. Capture the spatiotemporal characteristics of EEG signals through hierarchical modeling, and optimize the components of EEG signals through estimation and prediction of hidden variables. Finally, the mean square error (MSE) is used as an evaluation indicator to compare and evaluate the denoising results. Empirical research has shown that the HRTS algorithm can not only effectively reduce runtime and better process high-dimensional data, but also significantly improve the quality of EEG signals, effectively suppress noise interference, and more accurately reflect the characteristics of brain activity. Compared to denoising algorithms such as Kalman filtering and Kalman wavelet filtering, the HRTS algorithm has more advantages in denoising EEG signals. © 2024, J. Network Intell. All rigjts reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Solar-Blind Photodetector with Ultrahigh Rectification Ratio and Photoresponsivity Based on the Mote2/Ta:Β-Ga2o3 Pn Junction

SSRN

引用

SSRN 2023年

作者： Zeng, Guang Zhang, Meng-Ru Chen, Yu-Chang Li, Xiao-Xi Chen, Ding-Bo Shi, Cai-Yu Zhao, Xue-Feng Chen, Na Wang, Ting-Yun Zhang, David Wei Lu, Hong-Liang State Key Laboratory of ASIC and System Shanghai Institute of Intelligent Electronics & Systems School of Microelectronics Fudan University Shanghai200433 China Jia-Shan Fudan Institute Zhejiang Province Jiaxing314100 China State Key Laboratory of Integrated Chip and System Frontier Institute of Chip and System Fudan University Shanghai200433 China Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute Communication and Data Science Shanghai University Shanghai200444 China

High-performance solar-blind photodetectors have attracted increasing attention due to their important implications in military, medical, and industrial applications. Among a large number of wide-bandgap semiconductors, the quasi-two-dimensional β-Ga2O3 material is considered as a novel candidate for the solar-blind region (200–280 nm) owing to its suitable bandgap and superior optoelectronic properties. Herein, we report an outstanding solar-blind photodetector based on the MoTe2/Ta:β-Ga2O3 pn junction, which exhibits excellent optoelectrical properties with a superhigh rectification ratio of ~107, an ultrahigh responsivity (R ~358.9 A/W), a large detectivity (D* ~3.1 × 1012 Jones), an excellent external quantum efficiency (EQE ~1.8 × 105%), a fast photoresponse (21.1/84.5 ms), and a high rejection ratio (~1.1 × 103) under forward bias (1.5 V) and deep-ultraviolet (UV) illumination. These superior photoresponses result from the rapid separation of photoexcited electron-hole pairs driven by the synergistic effect of the forward bias and built-in electric field of the pn junction. Moreover, the MoTe2/Ta:β-Ga2O3 pn junction photodetector also demonstrates competitive optoelectronic characteristics in self-powered mode with a ultralow dark current of 8.5 fA and a fairly high R of 9.2 mA/W. As a result, this work provides an alternative solution for designing and fabricating high-performance solar-blind photodetectors with potential applications in UV imaging, environmental monitoring, and insecure communication. © 2023, The Authors. All rights reserved.

关键词： Military applications

来源：评论

学校读者我要写书评

暂无评论

SFTA: Spiking Neural Networks Vulnerable to Spiking Feature Transferable Attack

SFTA: Spiking Neural Networks Vulnerable to Spiking Feature ...

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Xuanwei Lin Chen Dong Ximeng Liu College of Computer and Data Science Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University) Key Lab of Information Security of Network Systems (Fuzhou University)

Many recent works have shown that spiking neural networks (SNNs) are vulnerable to well-crafted adversarial attacks in the white-box setting, which may lead to misclassification of the trained model. However, the information about the model is in a black-box setting and is usually unknown to the attacker, e.g., the parameters and structure of the model. So it is more challenging to counter the attack in the black-box setting, and there is still little research on this aspect in SNNs. Therefore, this work describes a transfer-based black box adversarial attack against spike feature space representations, providing insights for robust spike features in SNNs models. The attack is explicitly designed to be transferable, and more robust feature gradients are obtained by accumulating the feature gradients of the intermediate layers. Then we can successfully attack the black-box model by suppressing robust positive features and enhancing negative features. Extensive experimental evaluation demonstrates the proposed method’s effectiveness and superior performance on static and neuromorphic datasets. i.e., The attack success is 89.72% and 90% on the static MNIST and CIFAR10 datasets, and 85.97% and 69.09% on the neuromorphic N-MNIST and CIFARO-DVS datasets.

关键词： Correlation Neuromorphics Neural networks Closed box Ubiquitous computing Optimization Glass box

来源：评论

学校读者我要写书评

暂无评论

Short-term Portfolio Optimization using Doubly Regularized Exponential Growth Rate

Short-term Portfolio Optimization using Doubly Regularized E...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Quanlong Guan Jinneng He Zhao-Rong Lai Yuyu Zhou Quming Jiang Ziliang Chen College of Information Science and Technology Jinan University Guangzhou China Guangdong Institute of Smart Education Jinan University Guangzhou China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China Guangdong-Macao Advanced Intelligent Computing Joint Laboratory Zhuhai China Chutian Dragon Co. Ltd Dongguan China School of Intelligent Systems Science and Engineering Jinan University China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In the realm of short-term portfolio optimization, the integration of machine learning with exponential growth rate techniques is gaining prominence. This paper introduces a novel approach for short-term portfolio optimization, termed Short-term Portfolio Optimization using Doubly Regularized EGR (SPODR), to address the challenges posed by limited data availability. SPODR utilizes radial basis functions for the effective identification of market trends, enabling improved stock market forecasts. The approach uniquely combines ℓ 1 and ℓ 2 -regularization, adhering to empirical financial principles, to strike a balance between risk and return in short-term portfolios. A key aspect of SPODR is addressing the complexity of its ElasticNet-like objective, which poses a challenge for traditional methods due to its online learning nature. To overcome this, we have developed an algorithm based on the log barrier interior-point method. This algorithm is adept at efficiently optimizing portfolio allocation, taking into account the specific constraints inherent in our approach. Extensive comparative experiments across five benchmark datasets demonstrate that SPODR significantly outperforms existing short-term portfolio optimization models. It achieves a right balance between return and risk. Furthermore, SPODR showcases efficient computational speed, enhancing its applicability in real-world financial settings.

关键词： Computational modeling Benchmark testing Market research Robustness Regulation Computational efficiency Resource management

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

A Botnet data Collection Method for Industrial Internet

A Botnet Data Collection Method for Industrial Internet

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Shu Jian Xian Bo Wang Chenli Lu Jiazhong Huang Yuanyuan Han Shuo School of Cybersecurity Chengdu University of Information Technology Chengdu Sichuan China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu Sichuan China Department of Statistics and Data Sciences Northwestern University Evanston IL USA

Industrial internet security is related to industrial production operations and national economic security. Network intrusion detection dataset in industrial control environment can effectively train detection models and mitigate network attacks, which is an indispensable component for industrial internet security. In this paper, we propose a data collection method for industrial Internet-oriented botnet by classifying traffic packets according to network traffic features and industrial control identification codes, containing the status of industrial control devices. This method can greatly improve the detection accuracy of the model in the industrial internet. To create a botnet incursion dataset in the industrial control environment, we simultaneously employed the existing industrial control devices to gather both industrial control and botnet network traffic. Finally, we used an AI-based model to detect the botnet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：