检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yuan, Haonan Sun, Qingyun Wang, Zhaonan Fu, Xingcheng Ji, Cheng Wang, Yongjian Jin, Bo Li, Jianxin SKLCCSE School of Computer Science and Engineering Beihang University China National Superior College for Engineers Beihang University China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University China The Third Research Institute of Ministry of Public Security China

Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks (DGNNs). Dynamic Graph Structure Learning (DGSL) offers a promising way to optimize graph structures. However, aside from encountering unacceptable quadratic complexity, it overly relies on heuristic priors, making it hard to discover underlying predictive patterns. How to efficiently refine the dynamic structures, capture intrinsic dependencies, and learn robust representations, remains under-explored. In this work, we propose the novel DG-Mamba, a robust and efficient Dynamic Graph structure learning framework with the Selective State Space Models (Mamba). To accelerate the spatio-temporal structure learning, we propose a kernelized dynamic message-passing operator that reduces the quadratic time complexity to linear. To capture global intrinsic dynamics, we establish the dynamic graph as a self-contained system with State Space Model. By discretizing the system states with the cross-snapshot graph adjacency, we enable the long-distance dependencies capturing with the selective snapshot scan. To endow learned dynamic structures more expressive with informativeness, we propose the self-supervised Principle of Relevant Information for DGSL to regularize the most relevant yet least redundant information, enhancing global robustness. Extensive experiments demonstrate the superiority of the robustness and efficiency of our DG-Mamba compared with the state-of-the-art baselines against adversarial attacks. © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Safecoder: A Machine-Learning-Based Encoding System to Embed Safety Identification Information into Qr Codes

SSRN

引用

SSRN 2023年

作者： Su, Hao Niu, Jianwei Liu, Xuefeng Atiquzzaman, Mohammed State Key Lab of VR Technology and System School of Computer Science and Engineering Beihang University Beijing China Industrial Technology Research Institute School of Information Engineering Zhengzhou University Zhengzhou China Hangzhou Innovation Institute Beihang University Hangzhou China School of Computer Science The University of Oklahoma Norman United States

In social networks, the Internet of Things, mobile computing, electronic commerce, and other fields, Quick Response (QR) codes have been widely used as the interface between online and offline scenarios. In offline lives, users can readily scan QR codes with smartphones to access online networks or remote devices. However, standard QR codes appear as random black-and-white modules that make users difficult to visually distinguish the encoding message in QR codes, which incurs users unwittingly to scan malicious QR codes distributed by hackers, and results in serious issues of cyber security and privacy leakage. In this paper, we propose a novel system that can embed safety identification information (SII) into QR codes, which conduces to avoid issues of cyber security and privacy leakage. Although some existing methods attempt to embed visual information into QR codes, these methods require complex pre-designed algorithms and leave some limitations in visual representation. Unlike them, our system employs the machine learning technique, which can naturally embed SII into QR codes without compromising the scanning-robustness and message preservation. Subjective and objective experiments show that our system can effectively produce embedded QR codes that are applicable in real-world life, and reach the state-of-the-art level. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

arXiv

引用

arXiv 2024年

作者： Xie, Jinxia Zhong, Bineng Mo, Zhiyi Zhang, Shengping Shi, Liangtao Song, Shuxiang Ji, Rongrong Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education China Guangxi Key Lab of Multi-Source Information Mining & Security China Guangxi Normal University Guilin541004 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University China School of Computer Science and Technology Harbin Institute of Technology China Media Analytics and Computing Lab School of Informatics Xiamen University China

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal information aggregation. Consequently, the spatio-temporal information is far away from being fully explored. To alleviate this issue, we propose an adaptive tracker with spatio-temporal transformers (named AQATrack), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components. Firstly, we introduce a set of learnable and autoregressive queries to capture the instantaneous target appearance changes in a sliding window fashion. Then, we design a novel attention mechanism for the interaction of existing queries to generate a new query in current frame. Finally, based on the initial target template and learnt autoregressive queries, a spatio-temporal information fusion module (STM) is designed for spatio-temporal formation aggregation to locate a target object. Benefiting from the STM, we can effectively combine the static appearance and instantaneous changes to guide robust tracking. Extensive experiments show that our method significantly improves the tracker’s performance on six popular tracking benchmarks: LaSOT, LaSOText, TrackingNet, GOT-10k, TNL2K, and *** and models will be here. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Essential proteins identification based on weak consensus model and neighborhood aggregation centrality

Essential proteins identification based on weak consensus mo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhipeng Hu Gaoshi Li Jingli Wu Xinlong Luo Jiafei Liu Wei Peng Xiaoshu Zhu Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin China College of Computer Science and Engineering Guangxi Normal University Guilin China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China School of Computer and Information Security & School of Software Engineering Guilin University of Electronic Science and Technology Guilin China

Essential proteins play an essential role in cell survival and replication. Currently, more and more computational methods are developed to identify essential proteins, which overcome the time-consuming, costly and inefficient shortcomings with biological experimental methods. In order to improve the recognition rate, some new methods by fusing multiple features are developed, but they seldom consider the connection among features. After analyzing a large number of methods based on multi-feature fusion, a weak consensus model to fuse features is proposed in this paper. Then, this paper uses the weak consensus model to fuse protein-protein interaction network, gene expression data, and orthologous data, thus proposing a new method, WOL. Then experiments are performed on one *** dataset. The results show that compared with WDC, PeC, ION, JDC, NCCO and E_POC, WOL has a higher recognition rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A flexible technique to select objects via convolutional neural network in VR space

引用

science China(Information sciences) 2020年第1期63卷 57-76页

作者： Huiyu LI Linwei FAN School of Computer Science and Technology Shandong University Shandong Province Key Lab of Digital Media Technology Shandong University of Finance and Economics Shandong Co-Innovation Center of Future Intelligent Computing Shandong Technology and Business University

Most studies on the selection techniques of projection-based VR systems are dependent on users wearing complex or expensive input devices, however there are lack of more convenient selection *** this paper, we propose a flexible 3 D selection technique in a large display projection-based virtual environment. Herein, we present a body tracking method using convolutional neural network(CNN) to estimate3 D skeletons of multi-users, and propose a region-based selection method to effectively select virtual objects using only the tracked fingertips of multi-users. Additionally, a multi-user merge method is introduced to enable users’ actions and perception to realign when multiple users observe a single stereoscopic *** comparing with state-of-the-art CNN-based pose estimation methods, the proposed CNN-based body tracking method enables considerable estimation accuracy with the guarantee of real-time performance. In addition, we evaluate our selection technique against three prevalent selection techniques and test the performance of our selection technique in a multi-user scenario. The results show that our selection technique significantly increases the efficiency and effectiveness, and is of comparable stability to support multi-user interaction.

关键词： convolutional neural network interaction techniques pose estimation virtual reality 3D selection

来源：评论

学校读者我要写书评

暂无评论

In2NeCT: Inter-class and Intra-class Neural Collapse Tuning for Semantic Segmentation of Imbalanced Remote Sensing Images 39

In2NeCT: Inter-class and Intra-class Neural Collapse Tuning ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Shen, Junao Hu, Qiyun Feng, Tian Wang, Xinyu Cui, Hui Wu, Sensen Zhang, Wei School of Software Technology Zhejiang University China State Key Lab of CAD&CG Zhejiang University China Department of Computer Science and Information Technology La Trobe University Australia School of Earth Sciences Zhejiang University China Innovation Center of Yangtze River Delta Zhejiang University China

ISBN: (纸本)157735897X

Remote sensing images (RSIs) are frequently characterized by multi-scale inter-class objects and inconsistently distributed objects due to scene limitations, which would cause a significant data imbalance challenging the corresponding semantic segmentation. Recent methods have leveraged various deep learning techniques to capture high-quality representations for RSI semantic segmentation, but are hardly capable of addressing the afore-mentioned challenge given their limited explorations toward the mechanisms behind the representations. The recently discovered Neural Collapse (NC) phenomenon in computer vision models suggests the simplex equiangular tight frame (ETF) as the optimal representation structure, which has motivated us to observe that the optimal structure of last-layer representations is disrupted and inter-class representations for minor classes tend to become closer to each other beacuse of data imbalance. To address these issues, we propose Inter-class and Intra-class Neural Collapse Tuning (In2NeCT) to optimize the representations that satisfy the simplex ETF, which facilitates the discrimination of inter-class representations and the coherence of intra-class representations. Extensive experiments on three datasets demonstrate that our In2NeCT consistently leads to significant improvements in performance and outperforms the state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Search for Gravitational Wave Probes - A Self-Supervised Learning for Pulsars Based on Signal Contexts

Search for Gravitational Wave Probes - A Self-Supervised Lea...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shen Wang Xiaofeng Cheng Ming Xie Yuhang Ling Chao Liu Mingmin Chi Pei Wang Zhongyi Sun Yabiao Wang School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China Zhejiang Lab Zhongshan PoolNet Technology Co. Ltd Zhongshan Fudan Joint Innovation Center China National Astronomical Observatories Chinese Academy of Sciences China Tencent Youtu Lab China

The recent successful detection of gravitational waves (GWs) at nanohertz based on pulsar timing arrays has underscored the growing significance of searching for new pulsars, which serve as valuable probes for GWs. However, one of the challenges in this endeavor is the lack of labeled data, which can lead to overfitting and poor generalization in supervised deep neural networks. In this paper, we propose a self-supervised pretext task based on signal con-texts to obtain discriminative radio signal representation. Specially, signal attentions are designed to enhance pulse signals within time-phase or frequency-phase images whenever a pulsar is detected. To validate our proposed model, we conducted experiments using the FAST public dataset with a significant improvement in recall and AUC compared to existing single and multimodal deep models with different attentions. As a result, we searched more than 30 new pulsars.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A deep learning system for predicting time to progression of diabetic retinopathy

引用

NATURE MEDICINE 2024年第2期30卷 358-359页

作者： [Anonymous] Shanghai Belt and Road International Joint Laboratory for Intelligent Prevention and Treatment of Metabolic Disorders Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Huadong Sanatorium Wuxi China Department of Ophthalmology Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong China Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Department of Ophthalmology Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing China Medical Records and Statistics Office Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Geriatrics Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Tech

We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR Plus can be integrated into the clinical workflow to promote individualized intervention strategies for the management of diabetic retinopathy.

关键词： Diabetes complications Machine learning Predictive markers

来源：评论

学校读者我要写书评

暂无评论

Impact-aware Maneuver Decision with Enhanced Perception for Autonomous Vehicle

Impact-aware Maneuver Decision with Enhanced Perception for ...

引用

International Conference on Data Engineering

作者： Shuncheng Liu Yuyang Xia Xu Chen Jiandong Xie Han Su Kai Zheng School of Computer Science and Engineering University of Electronic Science and Technology of China China Huawei Cloud Database Innovation Lab China Yangtze Delta Region Institute (Quzhou) University of Electronic Science and Technology of China China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China

Autonomous driving is an emerging technology that has developed rapidly over the last decade. There have been numerous interdisciplinary challenges imposed on the current transportation system by autonomous vehicles. In this paper, we conduct an algorithmic study on the autonomous vehicle decision-making process, which is a fundamental problem in the vehicle automation field and the root cause of most traffic congestion. We propose a perception-and-decision framework, called HEAD, which consists of an enHanced pErception module and a mAneuver Decision module. HEAD aims to enable the autonomous vehicle to perform safe, efficient, and comfortable maneuvers with minimal impact on other vehicles. In the enhanced perception module, a graph-based state prediction model with a strategy of phantom vehicle construction is proposed to predict the one-step future states for multiple surrounding vehicles in parallel, which deals with sensor limitations such as limited detection range and poor detection accuracy under occlusions. Then in the maneuver decision module, a deep reinforcement learning-based model is designed to learn a policy for the autonomous vehicle to perform maneuvers in continuous action space w.r.t. a parameterized action Markov decision process. A hybrid reward function takes into account aspects of safety, efficiency, comfort, and impact to guide the autonomous vehicle to make optimal maneuver decisions. Extensive experiments offer evidence that HEAD can advance the state of the art in terms of both macroscopic and microscopic effectiveness.

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：