检索结果-内蒙古大学图书馆

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Li, He Yang, Shuaipeng Liu, Jinjiang Fang, Honglin Fu, Zhumu Zhang, Rui Jia, Huimei Lv, Lianmeng Henan Costar Group Co. Ltd Henan Nanyang473003 China Henan University of Science and Technology College of Information Engineering Henan Luoyang471000 China Nanyang Normal University Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image School of Computer Science and Technology Nanyang473061 China Beijing University of Posts and Telecommunication State Key Laboratory of Networking and Switching Technology Beijing100876 China Xi'an Hengpin Electronic Technology Co. Ltd Xi'an710100 China

ISBN: (纸本)9798350321524

With the development and application of computer vision, many target detection networks are applied to the detection of floating objects in rivers. For the detection problems such as small targets easily missed and misdetected in water surface floating object detection tasks and difficult to deploy models. An edge computing-oriented approach to river floater detection is proposed. First, a four-fold down-sampling feature layer is added to the YOLOv5 network which enhances more target detail features and improves the detection capability of small objects. Second, CA (Coordinate Attention) is added to the Backbone to suppress background noise interference, and different pooling is used to accommodate different hierarchical features. Then, a bilinear interpolation method is adopted for up-sampling to avoid the loss of small object features. Design a data enhancement algorithm for small targets based on Mosaic to increase the number of small objects and enrich the training background. Finally, for the edge computing architecture platform, the channel pruning algorithm is used to prune and compress the model structure to adapt to the computing capability of edge devices. The experimental results show that the method can effectively improve the detection capability of the network for floating objects on the water surface. The detection accuracy can reach 93.6%, and the detection speed can be maintained at 36 frames per second, which can achieve high-precision real-time detection of floating objects on the water surface. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation

arXiv

引用

arXiv 2025年

作者： Li, Jiachen Xie, Qing Yu, Xiaohan Wang, Hongyun Xu, Jinyu Liu, Yongjian Gao, Yongsheng School of Computer Science and Artificial Intelligence Wuhan University of Technology Hubei Wuhan430070 China Engineering Research Center of Intelligent Service Technology for Digital Publishing Ministry of Education Hubei Wuhan430070 China School of Computing Macquarie University SydneyNSW2109 Australia School of Engineering and Built Environment Griffith University NathanQLD4111 Australia

Zero-shot referring image segmentation aims to locate and segment the target region based on a referring expression, with the primary challenge of aligning and matching semantics across visual and textual modalities without training. Previous works address this challenge by utilizing Vision-Language Models and mask proposal networks for region-text matching. However, this paradigm may lead to incorrect target localization due to the inherent ambiguity and diversity of free-form referring expressions. To alleviate this issue, we present LGD (Leveraging Generative Descriptions), a framework that utilizes the advanced language generation capabilities of Multi-Modal Large Language Models to enhance region-text matching performance in Vision-Language Models. Specifically, we first design two kinds of prompts, the attribute prompt and the surrounding prompt, to guide the Multi-Modal Large Language Models in generating descriptions related to the crucial attributes of the referent object and the details of surrounding objects, referred to as attribute description and surrounding description, respectively. Secondly, three visual-text matching scores are introduced to evaluate the similarity between instance-level visual features and textual features, which determines the mask most associated with the referring expression. The proposed method achieves new state-of-the-art performance on three public datasets RefCOCO, RefCOCO+ and RefCOCOg, with maximum improvements of 9.97% in oIoU and 11.29% in mIoU compared to previous methods. Copyright © 2025, The Authors. 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

Human-like conceptual representations emerge from language prediction

arXiv

引用

arXiv 2025年

作者： Xu, Ningyu Zhang, Qi Du, Chao Luo, Qiang Qiu, Xipeng Huang, Xuanjing Zhang, Menghan School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China Ministry of Education Key Laboratory of Contemporary Anthropology Fudan University Shanghai China

People acquire concepts through rich physical and social experiences and use them to understand the world. In contrast, large language models (LLMs), trained exclusively through next-token prediction over language data, exhibit remarkably human-like behaviors. Are these models developing concepts akin to humans, and if so, how are such concepts represented and organized? To address these questions, we reframed the classic reverse dictionary task to simulate human concept inference in context and investigated the emergence of human-like conceptual representations within LLMs. Our results demonstrate that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts. The derived representations converged towards a shared, context-independent structure that effectively predicted human behavior across key psychological phenomena, including computation of similarities, categories and semantic scales. Moreover, these representations aligned well with neural activity patterns in the human brain, even in response to visual rather than linguistic stimuli, providing evidence for biological plausibility. These findings establish that structured, human-like conceptual representations can naturally emerge from language prediction without real-world grounding. More broadly, our work positions LLMs as promising computational tools for understanding complex human cognition and paves the way for better alignment between artificial and human intelligence. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Joint Extraction of Biomedical Entities and Relations based on Decomposition and Recombination Strategy

Joint Extraction of Biomedical Entities and Relations based ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qiang Zhu Cheng Hong Bangchao Wang Xinrong Hu Jie Yang Junping Liu Engineering Research Center of Hubei Province for Clothing Information Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion School of Computer Science and Artificial Intelligence Wuhan Textile University School of Computing and Information Technology University of Wollongong

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Entities and relations extraction is one of the key task to build medical knowledge graph, which is of great significance to the development of medical artificial intelligence. However, overlapping triples are great challenge for biomedical entities and relations extraction. In order to improve the performance of biomedical entities and relations extraction, we propose a joint extraction of entities and relations method based on decomposition and recombination strategy to mine biomedical text. Our method decomposes entities and relations extraction task into three related sub-modules, which are entity tagging module, relation classification module and recombination matching module. Our main contributions are as follows: first, we introduce a decomposition and recombination end-to-end learning framework for joint entities and relations extraction. Second, we propose a bi-directional prediction method to deal with the overlapping triples problem. Finally, we propose the negative samples generation method to alleviate the error accumulation among these modules. The extensive experiments demonstrate that our method can improve the F1 score by 4.36%, 2.13% and 11.72% in ADE, DDI and BB biomedical corpus.

关键词： Prediction methods Bidirectional control Tagging Data mining Task analysis Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Robust Android Malware Familial Classification

引用

IEEE Transactions on Dependable and Secure computing 2022年 1-14页

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China University of Texas at Dallas Dallas USA 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 Technology Huazhong University of Science and Technology Wuhan China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DH-Based Updatable Private Set Intersection

引用

International Journal of Network Security 2024年第6期26卷 1092-1101页

作者： Zhang, Yingbo Liu, Momeng Li, Yunyun Networking and Intelligent Information Services School of Computer Science Xi’an Polytechnic University State Key Laboratory of Integrated Services Networks Xidian University Shaanxi Key Laboratory of Clothing Intelligence State and Local Joint Engineering Research Center for Advanced No. 58 Shan-gu Road Lintong Xi’an710600 China

The rapid development of information technology provides convenience for online shopping, and many merchants try to increase their income through advertising conversion rates. However, in a virtual network environment, the transaction carries risks that may lead to private data leakage. Fortunately, private set intersection (PSI) provides an effective private data protection solution, allowing two parties to compute the intersection of their private sets without revealing any additional information beyond the intersection itself. This paper proposes an updatable PSI with a Diffie-Hellman-based key agreement paradigm. Our scheme allows dynamic updating of private sets of advertisers or merchants for computation, breaking the limitations of static scenarios. At the same time, we choose Rank and Select based Quotient Filter (RSQF) to process the data sets of participants in the scenario, it only needs small storage space to filter advertising data than Cuckoo filter. In addition, it allows merge operations between filters, and the filter is rebuilt when it reaches its maximum capacity without generating a new filter from scratch. Finally, we conducted comparison experiments and found that our solution has lower communication complexity and running time than related works. © (2024), (International Journal of Network Security). All rights reserved.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Graph Contrastive Learning 35

An Empirical Study of Graph Contrastive Learning

引用

35th Conference on Neural Information Processing Systems - Track on Datasets and Benchmarks, NeurIPS Datasets and Benchmarks 2021

作者： Zhu, Yanqiao Xu, Yichen Liu, Qiang Wu, Shu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Computer Science Beijing University of Posts and Telecommunications China

Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been witnessed recently, the success behind GCL is still left somewhat mysterious. In this work, we first identify several critical design considerations within a general GCL paradigm, including augmentation functions, contrasting modes, contrastive objectives, and negative mining strategies. Then, to understand the interplay of different GCL components, we conduct comprehensive, controlled experiments over benchmark tasks on datasets across various domains. Our empirical studies suggest a set of general receipts for effective GCL, e.g., simple topology augmentations that produce sparse graph views bring promising performance improvements;contrasting modes should be aligned with the granularities of end tasks. In addition, to foster future research and ease the implementation of GCL algorithms, we develop an easy-to-use library PyGCL, featuring modularized CL components, standardized evaluation, and experiment management. We envision this work to provide useful empirical evidence of effective GCL algorithms and offer several insights for future research. © 2021 Neural information processing systems foundation. 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

High-Level Synthesis for Microfluidic Biochips Considering Actual Volume Management and Channel Storage

High-Level Synthesis for Microfluidic Biochips Considering A...

引用

IEEE International Symposium on Quality Electronic Design

作者： Zhengyang Chen Yuhan Zhu Zhen Chen Zhisheng Chen Genggeng Liu College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University) Fuzhou China School of Informatics Xiamen University Xiamen China

ISBN: (数字)9798350309270

ISBN: (纸本)9798350309287

In recent years, microfluidic biochips have been widely applied in various fields of human society. The emergence of distributed channel-storage architecture enables fluid to be directly cached within the flow channels without being transported to the dedicated storage. However, the volume of the flow channels is limited, it is important to carefully consider the fluid volume to be cached to ensure it can be accommodated within the appropriate flow channels. In this paper, we propose a high-level synthesis method considering actual volume management and channel storage through integer linear programming, providing a rational analysis of fluid caching and the temporal relationships between different fluid-handling tasks. Experimental results conducted on multiple benchmark tests demonstrate the effectiveness of the proposed method in reducing the completion time of bioassay, the number of caches, the maximum fluid caching volume, and the number of fluid-handling tasks.

关键词： Fluids Biochips Estimation Cells (biology) Integer linear programming Benchmark testing Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Sparse-Point Guided Photometric Stereo Method for the Metal Complex Surfaces Measurement and High-Fidelity Geometry Recovery

SSRN

引用

SSRN 2023年

作者： Sun, Li Jian Cao, Weiqiang Bian, Yong Ren, Jie Ji Xu, Xiao Gang Intelligent Computing Platform Research Center Zhejiang Laboratory Zhejiang311121 China School of Computer Science Hangzhou Dianzi University Zhejiang310018 China School of Mechanical Engineering Institute of Robotics Shanghai Jiao Tong University Shanghai200240 China School of Computer and information Engineering Zhejiang Gongshang University Zhejiang310018 China

Accurate reconstruction of complex surfaces often requires informative measurement data with high accuracy, which poses a great challenge for measurement. In this paper, a contact sensor and a photometric stereo (PS) vision device are integrated together to recover the geometry with high-fidelity details. Then a two-branch deep PS neural network is developed and the Gaussian process regression (GPR) is used to reconstruct a global geometric shape from some sparse points captured by the contact probe. This prior geometry is sent to the proposed cross-convolution attention residual block (CCARB) based network to guide the PS for better normal recovery. The resulting normals are further fused with the sparse points by a normal integral model to obtain dense and high-accuracy points. Synthetic datasets are constructed to train the network. Experiments are conducted on both synthetic and real data, and show the superiority in the high-fidelity reconstruction for the measurement of complex surfaces. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Iterative Method to Analyze Misbehavior in Blockchain by Transaction Graph Matrix

A Iterative Method to Analyze Misbehavior in Blockchain by T...

引用

Information Communication and Software Engineering (ICICSE), IEEE International Conference on

作者： Jian Liu Shaohua Zhang Lai Wei Ruoting Xiong Wei Ren China Electronic Product Reliability Environmental Testing Research Institute Guangzhou China China Construction Eighth Engineering Division Shanghai China Department of Computing Science University of East Anglia Norfolk UK School of Computer Science China University of Geosciences Wuhan China Anhui Engineering Research Center of Intelligent Perception and Elderly Care Chuzhou University Chuzhou China

ISBN: (数字)9798350351699

ISBN: (纸本)9798350351705

Blockchain provides an publicly accessed and accepted ledger without centralized control among open participators. The anonymity in payments and transactions may results in possible misbehaviors, e.g., money laundry. Fortunately, the transaction data is open and can be analyzed. In this paper, we propose The major challenges are the data volume is large and the global view of transactions in terms of hops and time sequences. In this paper, we address the transactions with multiple intermediators, and graph dynamics with time-spans. The analyzing models and computing algorithms are proposed. The extensive and formal analysis justifies the soundness of our proposed methods.

关键词： Analytical models Computational modeling Heuristic algorithms Data models Blockchains Iterative methods Software engineering

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：