检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Wenhao Wang, Changwei Feng, Xuxiang Xu, Rongtao Huang, Longzhao Zhang, Zherui Guo, Li Xu, Shibiao School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250013 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China The Aerospace Information Research Institute Chinese Academy of Sciences China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation. However, directly applying VLMs to such tasks remains challenging due to their lack of pixel-level granularity and the limited data available for fine-tuning, leading to overfitting and poor generalization. To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation. GBA comprises two core components: (1) a Style Diversification Adapter (SDA) that decouples features into amplitude and phase components, operating solely on the amplitude to enrich the feature space representation while preserving semantic consistency;and (2) a Correlation Constraint Adapter (CCA) that employs cross-attention to establish tighter semantic associations between text categories and target regions, suppressing irrelevant low-frequency "noise" information and avoiding erroneous associations. Through the synergistic effect of the shallow SDA and the deep CCA, GBA effectively alleviates overfitting issues and enhances the semantic relevance of feature representations. As a simple, efficient, and plug-and-play component, GBA can be flexibly integrated into various CLIP-based methods, demonstrating broad applicability and achieving state-of-the-art performance on multiple open-vocabulary segmentation benchmarks. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

GUEST EDITORIAL

引用

China Communications 2023年第2期 3-6页

作者： Yuan Wu Xu Chen Feng Lyu Xianfu Chen Xumin Huang Jie Gao Yueyue Dai Tony Q.S.Quek Yan Zhang the State Key Laboratory of Internet of Things for Smart City University of Macau the Department of Computer and Information Science University of Macau Sun Yat-sen University Sun Yat-sen University Institute of Advanced Networking and Computing Systems Sun Yat-sen University National and Local Joint Engineering Laboratory the School of Computer Science and Engineering Central South University the VTT Technical Research Centre of Finland the School of Automation Guangdong University of Technology the School of Information Technology Carleton University Huazhong University of Science and Technology Singapore University of Technology and Design(SUTD) the IEEE Communications Society Technical Committee on Green Communications and Computing(TCGCC)

With the growing maturity of the advanced edge-cloud collaboration and integrated sensing-communication-computing systems, edge intelligence has been envisioned as one of the enabling technologies for ubiquitous and l...

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAMamba: Adaptive state space modeling with hierarchical vision for infrared small target detection

引用

Information Fusion 2025年 124卷

作者： Xu, Wenhao Zheng, Shuchen Wang, Changwei Zhang, Zherui Ren, Chuan Xu, Rongtao Xu, Shibiao School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Jinan250014 China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250014 China School of Software Microelectronics Peking University Beijing100084 China

Infrared small target detection (ISTD) is vital for long-range surveillance systems, particularly in military defense, maritime monitoring, and early warning applications. Despite its strategic importance, ISTD remains challenging due to two fundamental limitations: targets typically occupy less than 0.15% of the image area and exhibit low distinguishability from complex backgrounds. While recent advances in deep learning have shown promise, existing methods struggle with information loss during downsampling and inefficient modeling of global context. This paper presents SAMamba, a novel framework that synergistically integrates SAM2's hierarchical feature learning with Mamba's selective sequence modeling to address these challenges. Our key innovations include: (1) Feature Selection Adapter (FS-Adapter) that enables efficient domain adaptation from natural to infrared imagery by employing a dual-stage selection mechanism, which includes token-level selection via a learnable task embedding and channel-wise refinement through adaptive transformations;(2) Cross-Channel State-Space Interaction (CSI) module that achieves efficient global context modeling through selective state space modeling with linear complexity;and (3) Detail-Preserving Contextual Fusion (DPCF) module that adaptively combines multi-scale features through learnable fusion strategies, utilizing a gating mechanism to balance contributions from high-resolution and low-resolution features. SAMamba effectively addresses the core challenges of ISTD by bridging the domain gap, maintaining fine-grained target details, and efficiently modeling long-range dependencies. Extensive experiments on NUAA-SIRST, IRSTD-1k and NUDT-SIRST datasets demonstrate that SAMamba significantly outperforms state-of-the-art methods, particularly in challenging scenarios with heterogeneous backgrounds and varying target scales. Code is available at https://***/zhengshuchen/SAMamba. © 2025 Elsevier B.V.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

GSLB: the graph structure learning benchmark 23

GSLB: the graph structure learning benchmark

引用

Proceedings of the 37th International Conference on neural Information Processing systems

作者： Zhixun Li Liang Wang Xin Sun Yifan Luo Yanqiao Zhu Dingshuo Chen Yingtao Luo Xiangxin Zhou Qiang Liu Shu Wu Jeffrey Xu Yu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences and Department of Automation University of Science and Technology of China Department of Automation University of Science and Technology of China School of Cyberspace Security Beijing University of Posts and Telecommunications Department of Computer Science University of California Los Angeles Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Prototypes Contrastive Learning for Semi-Supervised Medical Image Segmentation

SSRN

引用

SSRN 2024年

作者： Yue, Tianai Xu, Rongtao Wu, Jingqian Yang, Wenjie Du, Shide Wang, Changwei Johns Hopkins University Baltimore21218 United States State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The University of Hong Kong Hong Kong999077 Hong Kong College of Computer and Big Data Fuzhou University Fuzhou350108 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan250014 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250014 China

Semi-supervised techniques for medical image segmentation have demonstrated potential, effectively training models using scarce labeled data alongside a wealth of unlabeled data. Therefore, semi-supervised medical image segmentation is one of the key issues in engineering applications of medical artificial intelligence. Consistency constraints based on prototype alignment provide an intuitively sensible way to discover valuable insights from unlabeled data that can motivate segmentation performance. In this work, we propose a dual prototypes contrastive network (DPC-Net) to motivate semi-supervised medical segmentation accuracy by imposing image-level global prototype constraints and pixel-level local prototype constraints. First, we introduce a Background-Separation Global Prototype Contrastive Learning technique that utilizes the natural mutual exclusivity of foreground and background to separate the inter-class distances and encourage the segmentation network to obtain segmentation results that are more complete and do not contain background regions. Second, we design a Cross-Consistent Local Prototype Contrastive Learning techniques to extend the perturbation consistency of the two networks to the prototype's localized response to the feature map, thereby shaping a more stable intra-class prototype space and producing accurate and robust pixel-level predictions. Finally, we comprehensively evaluate our method on mainstream semi-supervised medical image segmentation benchmarks and settings, and experimental results show that our DPC-Net outperforms current state-of-the-art methods. © 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

Soccer match broadcast video analysis method based on detection and tracking

Soccer match broadcast video analysis method based on detect...

引用

作者： Li, Hongyu Yang, Meng Yang, Chao Kang, Jianglang Suo, Xiang Meng, Weiliang Li, Zhen Mao, Lijuan Sheng, Bin Qi, Jun School of Information science and Technology Beijing Forestry University Beijing China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration Beijing China School of Athletic Performance Shanghai University of Sport Shanghai China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong Univerity Shanghai China Department of Computing Xi'an JiaoTong-Liverpool University Suzhou China

We propose a comprehensive soccer match video analysis pipeline tailored for broadcast footage, which encompasses three pivotal stages: soccer field localization, player tracking, and soccer ball detection. Firstly, we introduce sports camera calibration to seamlessly map soccer field images from match videos onto a standardized two-dimensional soccer field template. This addresses the challenge of consistent analysis across video frames amid continuous camera angle changes. Secondly, given challenges such as occlusions, high-speed movements, and dynamic camera perspectives, obtaining accurate position data for players and the soccer ball is non-trivial. To mitigate this, we curate a large-scale, high-precision soccer ball detection dataset and devise a robust detection model, which achieved the (Formula presented.) of 80.9%. Additionally, we develop a high-speed, efficient, and lightweight tracking model to ensure precise player tracking. Through the integration of these modules, our pipeline focuses on real-time analysis of the current camera lens content during matches, facilitating rapid and accurate computation and analysis while offering intuitive visualizations. © 2024 John Wiley & Sons Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Advances in Embodied Navigation Using Large Language Models: A Survey

arXiv

引用

arXiv 2023年

作者： Lin, Jinzhou Gao, Han Feng, Xuxiang Xu, Rongtao Wang, Changwei An, Dong Zhou, Jie Zhang, Man Guo, Li Teng, Xiaoqiang Xu, Shibiao School of Artificial Intelligence Beijing University of Posts and Telecommunications China Aerospace Information Research Institute Chinese Academy of Science China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China Qilu University of Technology Shandong Academy of Sciences China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250014 China School of Computer and Artificial Intelligence Beijing Technology and Business Unicersitu China

Large Language Models like GPT have gained significant attention for their potential in various practical applications. One notable area of focus is their integration with Embodied Intelligence, particularly in navigation tasks, which require deep environmental understanding and rapid, accurate decision-making. LLMs enhance embodied intelligence systems by providing advanced environmental perception and decision-making support, leveraging their language and image-processing capabilities. This article reviews the symbiosis between LLMs and embodied intelligence, focusing on navigation, and evaluates current models, research methodologies, and datasets. Additionally, it discusses the role of LLMs in the field and forecasts future research directions. A comprehensive list of studies is available at https://***/Rongtao-Xu/AwesomeLLM-EN. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Offsite Evaluation of Localization systems: Criteria, systems, and Results From IPIN 2021 and 2022 Competitions

IEEE Journal on Indoor and Seamless Positioning and Navigati...

引用

IEEE Journal on Indoor and Seamless Positioning and Navigation 2024年 2卷 92-129页

作者： Potorti, Francesco Crivello, Antonino Lee, Soyeon Vladimirov, Blagovest Park, Sangjoon Chen, Yushi Wang, Long Chen, Runze Zhao, Fang Zhuge, Yue Luo, Haiyong Perez-Navarro, Antoni Jimenez, Antonio R. Wang, Han Liang, Hengyi De Cock, Cedric Plets, David Cui, Yan Xiong, Zhi Li, Xiaodong Ding, Yiming Franco, Fernando Javier Alvarez Polo, Fernando Jesus Aranda Rodriguez, Felipe Parralejo Moreira, Adriano Pendao, Cristiano Silva, Ivo Ortiz, Miguel Zhu, Ni Li, Ziyou Renaudin, Valerie Wei, Dongyan Ji, Xinchun Zhang, Wenchao Wang, Yan Ding, Longyang Kuang, Jian Zhang, Xiaobing Dou, Zhi Yang, Chaoqun Kram, Sebastian Stahlke, Maximilian Mutschler, Christopher Coene, Sander Li, Chenglong Venus, Alexander Leitinger, Erik Tertinek, Stefan Witrisal, Klaus Wang, Yi Wang, Shaobo Jin, Beihong Zhang, Fusang Su, Chang Wang, Zhi Li, Siheng Li, Xiaodong Li, Shitao Pan, Mengguan Zheng, Wang Luo, Kai Ma, Ziyao Gao, Yanbiao Chang, Jiaxing Ren, Hailong Guo, Wenfang Torres-Sospedra, Joaquin Pisa56124 Italy Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Beijing University of Posts and Telecommunications School of Computer Science National Pilot Software Engineering School Beijing100876 China Chinese Academy of Sciences Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Beijing100190 China Universitat Oberta de Catalunya Faculty of Computer Sciences Multimedia and Telecommunication Barcelona08035 Spain Arganda del Rey28500 Spain Huawei Technologies Company Ltd. Shenzhen100015 China IMEC-WAVES/Ghent University Department of Information Technology Gent9052 Belgium Nanjing University of Aeronautics and Astronautics College of Automation Nanjing210016 China University of Extremadura Badajoz06006 Spain University of Trás-os-Montes and Alto Douro Department of Engineering School of Sciences and Technology Vila Real5000-801 Portugal Universidade Do Minho Centro Algoritmi Guimarães4800-058 Portugal Ame Department of the University Gustave Eiffel Geoloc Laboratory Bouguenais44344 France Chinese Academy of Sciences Aerospace Information Research Institute Beijing100094 China Wuhan University Gnss Research Center Wuhan430072 China AutoNavi Software Company Ltd. China Fraunhofer Institute for Integrated Circuits Iis Fraunhofer Iis Nuremberg90411 Germany Erlangen91058 Germany Graz University of Technology Christian Doppler Laboratory for Location-Aware Electronic Systems Graz8010 Austria Institute of Software Chinese Academy of Sciences Beijing100190 China Purple Mountain Laboratories Pervasive Communication Research Center Nanjing210000 China Beijing University of Posts and Telecommunications Beijing100876 China

Indoor positioning is a thriving research area, which is slowly gaining market momentum. Its applications are mostly customized, ad hoc installations;ubiquitous applications analogous to Global Navigation Satellite System for outdoors are not available because of the lack of generic platforms, widely accepted standards and interoperability protocols. In this context, the indoor positioning and indoor navigation (IPIN) competition is the only long-term, technically sound initiative to monitor the state of the art of real systems by measuring their performance in a realistic environment. Most competing systems are pedestrian-oriented and based on the use of smartphones, but several competing tracks were set up, enabling comparison of an array of technologies. The two IPIN competitions described here include only off-site tracks. In contrast with on-site tracks where competitors bring their systems on-site - which were impossible to organize during 2021 and 2022 - in off-site tracks competitors download prerecorded data from multiple sensors and process them using the EvaalAPI, a real-time, web-based emulation interface. As usual with IPIN competitions, tracks were compliant with the EvAAL framework, ensuring consistency of the measurement procedure and reliability of results. The main contribution of this work is to show a compilation of possible indoor positioning scenarios and different indoor positioning solutions to the same problem. © 2023 CCBY.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection

arXiv

引用

arXiv 2024年

作者： Xu, Shibiao Zheng, ShuChen Xu, Wenhao Xu, Rongtao Wang, Changwei Zhang, Jiguang Teng, Xiaoqiang Li, Ao Guo, Li Artificial Intelligence Beijing University of Posts and Telecommunications China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science China School of Computer Science and Technology Harbin University of Science and Technology China

Infrared small object detection is an important computer vision task involving the recognition and localization of tiny objects in infrared images, which usually contain only a few pixels. However, it encounters difficulties due to the diminutive size of the objects and the generally complex backgrounds in infrared images. In this paper, we propose a deep learning method, HCF-Net, that significantly improves infrared small object detection performance through multiple practical modules. Specifically, it includes the parallelized patch-aware attention (PPA) module, dimension-aware selective integration (DASI) module, and multi-dilated channel refiner (MDCR) module. The PPA module uses a multi-branch feature extraction strategy to capture feature information at different scales and levels. The DASI module enables adaptive channel selection and fusion. The MDCR module captures spatial features of different receptive field ranges through multiple depth-separable convolutional layers. Extensive experimental results on the SIRST infrared single-frame image dataset show that the proposed HCF-Net performs well, surpassing other traditional and deep learning models. Code is available at https://***/zhengshuchen/HCFNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Method

arXiv

引用

arXiv 2024年

作者： Zou, Hang Du, Chenxi Liu, Ajian Zhang, Yuan Liu, Jing Yang, Mingchuan Wan, Jun Zhang, Hui Sun, Zhenan China Telecom Research Institute Beijing 102209 Shanghai200122 China Shenzhen518055 China Shenzhen518055 China Shenzhen518107 China Beijing100190 China School of Computer Science and Engineering Macau University of Science and Technology China Tianjin University of Science & Technology Tianjin300457 China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Iris recognition is widely used in high-security scenarios due to its stability and distinctiveness. However, iris images captured by different devices exhibit certain and device-related consistent differences, which has a greater impact on the classification algorithm for anti-spoofing. The iris of various races would also affect the classification, causing the risk of identity theft. So it is necessary to improve the cross-domain capabilities of the iris anti-spoofing (IAS) methods to enable it more robust in facing different races and devices. However, there is no existing protocol that is comprehensively available. To address this gap, we propose an Iris Anti-Spoofing Cross-Domain-Testing (IAS-CDT) Protocol, which involves 10 datasets, belonging to 7 databases, published by 4 institutions, and collected with 6 different devices. It contains three sub-protocols hierarchically, aimed at evaluating average performance, cross-racial generalization, and cross-device generalization of IAS models. Moreover, to address the cross-device generalization challenge brought by the IAS-CDT Protocol, we employ multiple model parameter sets to learn from the multiple sub-datasets. Specifically, we utilize the Mixture of Experts (MoE) to fit complex data distributions using multiple sub-neural networks. To further enhance the generalization capabilities, we propose a novel method Masked-MoE (MMoE), which randomly masks a portion of tokens for some experts and requires their outputs to be similar to the unmasked experts, which can effectively mitigate the overfitting issue of MoE. For the evaluation, we selected ResNet50, VIT-B/16, CLIP, and FLIP as representative Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

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：