检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhao, Yifan Li, Jia Song, Zeyin Tian, Yonghong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China School of Electronic and Computer Engineering Peking University Shenzhen518055 China School of Computer Science Peking University Beijing100871 China Pengcheng Laboratory Shenzhen518055 China

Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems. This lifelong learning capability helps to distinguish new knowledge from old ones through the increase of open-world learning, namely Few-Shot Class-Incremental Learning (FSCIL). Existing works to solve this problem mainly rely on the careful tuning of visual encoders, which shows an evident trade-off between the base knowledge and incremental ones. Motivated by human learning systems, we propose a new Language-inspired Relation Transfer (LRT) paradigm to understand objects by joint visual clues and text depictions, composed of two major steps. We first transfer the pretrained text knowledge to the visual domains by proposing a graph relation transformation module and then fuse the visual and language embedding by a text-vision prototypical fusion module. Second, to mitigate the domain gap caused by visual finetuning, we propose context prompt learning for fast domain alignment and imagined contrastive learning to alleviate the insufficient text data during alignment. With collaborative learning of domain alignments and text-image transfer, our proposed LRT outperforms the state-of-the-art models by over 13% and 7% on the final session of miniImageNet and CIFAR-100 FSCIL benchmarks. Copyright © 2025, 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

II-NVM: Enhancing Map Accuracy and Consistency With Normal Vector-Assisted Mapping

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5465-5472页

作者： Zhao, Chengwei Li, Yixuan Jian, Yina Xu, Jie Wang, Linji Ma, Yongxin Jin, Xinglai Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China Hangzhou Qisheng Intelligent Techology Company Ltd Hangzhou311217 China Columbia University in the City of New York Department of Computer Science New YorkNY10027 United States Harbin Institute of Technology State Key Laboratory of Robotics and Systems Harbin150001 China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore

SLAM technology plays a crucial role in indoor mapping and localization. A common challenge in indoor environments is the "double-sided mapping issue", where closely positioned walls, doors, and other surfaces are mistakenly identified as a single plane, significantly hindering map accuracy and consistency. To addressing this issue this letter introduces a SLAM approach that ensures accurate mapping using normal vector consistency. We enhance the voxel map structure to store both point cloud data and normal vector information, enabling the system to evaluate consistency during nearest neighbor searches and map updates. This process distinguishes between the front and back sides of surfaces, preventing incorrect point-to-plane constraints. Moreover, we implement an adaptive radius KD-tree search method that dynamically adjusts the search radius based on the local density of the point cloud, thereby enhancing the accuracy of normal vector calculations. To further improve real-time performance and storage efficiency, we incorporate a Least Recently Used (LRU) cache strategy, which facilitates efficient incremental updates of the voxel map. The code is released as open-source and validated in both simulated environments and real indoor scenarios. Experimental results demonstrate that this approach effectively resolves the "double-sided mapping issue" and significantly improves mapping precision. Additionally, we have developed and open-sourced the first simulation and real-world dataset specifically tailored for the "double-sided mapping issue". © 2016 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

EvoPath: Evolutionary Meta-path Discovery with Large Language Models for Complex Heterogeneous Information Networks

arXiv

引用

arXiv 2025年

作者： Liu, Shixuan Cheng, Haoxiang Wang, Yunfei He, Yue Fan, Changjun Liu, Zhong Laboratory for Big Data and Decision College of Systems Engineering National University of Defense Technology Hunan Changsha China National Key Laboratory of Information Systems Engineering College of Systems Engineering National University of Defense Technology Hunan Changsha China Department of Computer Science and Technology Tsinghua University Beijing China

Heterogeneous Information Networks (HINs) encapsulate diverse entity and relation types, with meta-paths providing essential meta-level semantics for knowledge reasoning, although their utility is constrained by discovery challenges. While Large Language Models (LLMs) offer new prospects for meta-path discovery due to their extensive knowledge encoding and efficiency, their adaptation faces challenges such as corpora bias, lexical discrepancies, and hallucination. This paper pioneers the mitigation of these challenges by presenting EvoPath, an innovative framework that leverages LLMs to efficiently identify high-quality meta-paths. EvoPath is carefully designed, with each component aimed at addressing issues that could lead to potential knowledge conflicts. With a minimal subset of HIN facts, EvoPath iteratively generates and evolves meta-paths by dynamically replaying meta-paths in the buffer with prioritization based on their scores. Comprehensive experiments on three large, complex HINs with hundreds of relations demonstrate that our framework, EvoPath, enables LLMs to generate high-quality meta-paths through effective prompting, confirming its superior performance in HIN reasoning tasks. Further ablation studies validate the effectiveness of each module within the framework. © 2025, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Facilitating Continuous Facial Aging through Latent Age Attribute Modulation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Hu, Xiyuan Qu, Jinglei Chen, Chen Beijing University of Technology School of Computer Science Beijing100124 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China

In recent years, facial aging has attracted significant research interest due to its broad applications and potential benefits. While Generative Adversarial Networks (GANs) have achieved notable progress in synthesizing realistic facial images, many GAN-based facial aging methods struggle to accurately capture the continuous progression of age-related changes over time. In this paper, we propose an innovative framework featuring the Latent Age Attribute Module (LAAM), which maps age attributes to a structured latent space that facilitates efficient sampling for precisely age attribute modeling. We further introduce the Age-AdaIN Fusion Module (AFM), which seamlessly integrates age features from LAAM with facial content features, enabling the generation of images that exhibit smooth, continuous age transitions. This framework excels in capturing fine-grained aging details, particularly for elderly individuals. Quantitative and qualitative evaluations on benchmark datasets demonstrate the effectiveness of our approach in generating realistic age-progressed facial images, with a notable improvement in elderly aging accuracy and detail. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

CNsum:Automatic Summarization for Chinese News Text

arXiv

引用

arXiv 2025年

作者： Zhao, Yu Huang, Songping Zhou, Dongsheng Ding, Zhaoyun Wang, Fei Nian, Aixin Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha410000 China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian116000 China

Obtaining valuable information from massive data efficiently has become our research goal in the era of Big Data. Text summarization technology has been continuously developed to meet this demand. Recent work has also shown that transformer-based pre-trained language models have achieved great success on various tasks in Natural Language Processing (NLP). Aiming at the problem of Chinese news text summary generation and the application of Transformer structure on Chinese, this paper proposes a Chinese news text summarization model (CNsum) based on Transformer structure, and tests it on Chinese datasets such as THUCNews. The results of the conducted experiments show that CNsum achieves better ROUGE score than the baseline models, which verifies the outperformance of the model. © 2025, CC BY.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Automated explainable and interpretable framework for anomaly detection and human activity recognition in smart homes

引用

Neural Computing and Applications 2025年 1-14页

作者： Kim, Tae Hoon Ojo, Stepehn Krichen, Moez Alamro, Meznah A. Mihoub, Alaeddine Sampedro, Gabriel Avelino School of Information and Electronic Engineering Zhejiang University of Science and Technology No. 318 Zhejiang Hangzhou China Department of Electrical and Computer Engineering College of Engineering Anderson Anderson University AndersonSC29621 United States Al-Baha University Al-Baha65528 Saudi Arabia ReDCAD Laboratory University of Sfax Sfax3038 Tunisia Department of Information Technology College of Computer and Information Science Princess Nourah Bint Abdul Rahman University Riyadh11564 Saudi Arabia Department of Management Information Systems College of Business and Economics Qassim University P.O. Box: 6640 Buraidah51452 Saudi Arabia College of Computer Studies De La Salle University 2401 Taft Ave. Malate Manila1004 Philippines Faculty of Information and Communication Studies University of the Philippines Open University Los Baños4031 Philippines

This paper presents a comprehensive framework for activity recognition and anomaly detection in smart home environments, targeting applications in convenience, efficiency, responsiveness, and healthcare. The proposed framework incorporates explainable artificial intelligence (XAI) to interpret feature impacts on learning models and optimize feature selection for activity recognition and anomaly detection. The study examines the recognition of two activity sets: Activities Set I, comprising 8 activities, and Activities Set II, comprising 11 activities. Various machine learning models (random forest (RF), decision tree (DT), and XGBoost (XGB)) are employed, along with an ensemble voting classifier (EVC) with these machine learning. EVC achieved 91% accuracy for Activities Set I and 90–91% accuracy for Activities Set II. The model demonstrated strong precision, recall, and F1-score across most classes. For anomaly detection, the Isolation Forest and H2O Isolation Forest Estimator algorithms are utilized to uncover irregularities in daily routines. The Isolation Forest identified anomalies in activities such as chores and desk-related tasks, while the H2O Isolation Forest Estimator detected no anomalies in either activity set. This study underscores the potential of the proposed framework to enhance smart home functionality and highlights avenues for future research and system improvements. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Real-Time, Robust, and Versatile Visual-SLAM Framework Based on Deep Learning Networks

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Zhang, Xiao Dong, Hongbin Zhang, Haoxin Zhu, Xiaozhou Li, Shuaixin Deng, Baosong Harbin Engineering University College of Computer Science and Technology National Engineering Laboratory for E-Government Modeling and Simulation Harbin150009 China Defense Innovation Institute Chinese Academy of Military Science Beijing100850 China Sun Yat-sen University College of Systems Science and Engineering Guangzhou510275 China Intelligent Game and Decision Laboratory Beijing100166 China

In this article, we investigate the paradigm of deep learning techniques to enhance the performance of visual-based simultaneous localization and mapping (vSLAM) systems, particularly in challenging environments. By leveraging deep feature extraction and matching methods, we propose a robust, versatile hybrid visual SLAM framework, Rover-SLAM, aimed at improving adaptability in adverse conditions, such as dynamic lighting conditions, areas with weak textures, and camera jitter. Building on excellent learning-based algorithms of recent years, we designed from scratch a novel system that uses the same feature extraction and matching approaches for all SLAM tasks. Our system supports multiple modes, including monocular, stereo, monocular-inertial, and stereo-inertial configurations, offering flexibility to address diverse real-world scenarios. Through comprehensive experiments conducted on publicly available datasets and self-collected data, we demonstrate the superior performance of our Rover-SLAM system compared to the state-of-the-art (SOTA) approaches. We also conducted an in-depth analysis of the integration of visual SLAM with deep learning methods quantitatively to provide insights for future research endeavors in this domain. The experimental results showcase the system's capability of achieving higher localization accuracy and robust tracking performance. © 1963-2012 IEEE.

关键词： Stereocenters

来源：评论

学校读者我要写书评

暂无评论

Mask-guided Multi-scale Spatial-Spectral Transformer for Snapshot Compressive Imaging

Mask-guided Multi-scale Spatial-Spectral Transformer for Sna...

引用

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

作者： Heyuan Yin Jingxiang Yang Jia Liu Liang Xiao School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Key Laboratory of Analysis of Mathematical Theory and Modeling of Complex Systems The Ministry of Industry and Information Technology China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Effectively reconstructing 3D hyperspectral images (HSIs) from 2D measurements presents a significant challenge in Coded Aperture Snapshot Spectral Imaging (CASSI) systems. While recent transformers exhibit potential in HSI reconstruction, they often suffer from inadequate exploration of multi-scale spatial-spectral self-similarity, leading to mean effects and information loss. Additionally, these methods struggle with insufficient modeling of the degradation inherent in the compressive imaging process. To address these issues, we propose a novel Mask-guided Multi-scale Spatial-Spectral Transformer (MMSST). Specifically, we introduce a Degradation Aware Mask Attention (DAMA) module to incorporate degradation information of the compressive imaging process. Furthermore, MMSST leverages Local-Regional SpAtial attention (LRSA) and Global-Regional SpEctral attention (GRSE) to effectively exploit multi-scale self-similarity across spatial and spectral dimensions. Extensive experimental results demonstrate the effectiveness of our MMSST.

关键词： Degradation Three-dimensional displays Computational modeling Imaging Transformer cores Signal processing Transformers Speech processing Image reconstruction Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

A Review of Pseudonym Change Strategies for Location Privacy Preservation Schemes in Vehicular Networks

引用

ACM Computing Surveys 2025年第8期57卷 1-37页

作者： Benarous, Leila Zeadally, Sherali Boudjit, Saadi Mellouk, Abdelhamid Department of Computer science Amar Telidji University of Laghouat Laghouat Algeria LISSI-Tinc-NET Laboratory University of Paris-Est Creteil Créteil France College of Communication and Information University of Kentucky Lexington United States Department of Electronic Engineering Kyung Hee University Seoul Korea Republic of Litis Lab Intelligent Transportation Systems Group University of Rouen Normandy Mont-Saint-Aignan France Lissi Laboratory Department of Networks and Telecom University Paris-Est Créteil Val de Marne Créteil France

Location privacy protection in vehicular networks has been a primary priority to ensure because of its direct impact on human physical safety. Leakage and violation of road users' location privacy may be perilous beyond simple curiosity as it may scale to cyberstalking and tracking. This may lead to road users being subjected to mental and physical distress, from blackmailing to targeted advertising, and trap planning. The results of tracking may be fatal to road users. Over the past 17 years, researchers have been actively investigating location privacy protection mechanisms for vehicular networks. Numerous research results have been published that examined the use of pseudonym change strategies, which have been considered as the most appropriate solution that maintains the tradeoff between ease of application, good protection level, and the correct functionality of the network. We evaluate, classify, and analyze pseudonym change strategies aimed at location privacy preserving solutions for vehicular networks and discuss their performance. We also review the simulation tools used for evaluating pseudonym change techniques used in location privacy preserving solutions for the vehicular environment. The results of this survey will help researchers in this field to develop more robust, efficient, and cost-effective location privacy protection schemes in the future. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

ON INFINITE-HORIZON MINIMUM ENERGY CONTROL

arXiv

引用

arXiv 2025年

作者： Belabbas, Mohamed-Ali Chen, Xudong Electrical and Computer Engineering Department and Coordinated Science Laboratory University of Illinois Urbana-Champaign United States Electrical and Systems Engineering Washington University in St. Louis United States

We address the infinite-horizon minimum energy control problem for linear time-invariant finite-dimensional systems (A, B). We show that the problem admits a solution if and only if (A, B) is stabilizable and A does n... 详细信息

关键词： Linear time-invariant system

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：