检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xie, Qiujie Li, Qingqiu Yu, Zhuohao Zhang, Yuejie Zhang, Yue Yang, Linyi Zhejiang University China School of Engineering Westlake University China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Peking University China Westlake Institute for Advanced Study China University College London United Kingdom Huawei Noah’s Ark Lab Hong Kong

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias, little research has concentrated on the stability of LLM evaluators. In this paper, we conduct extensive experiments involving 9 widely used LLM evaluators across 2 different evaluation settings to investigate the uncertainty in model-based LLM evaluations. We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes. With careful comparative analyses, we find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent. By utilizing uncertainty to enhance LLM’s reliability and detection capability in Out-Of-Distribution (OOD) data, we further fine-tune an uncertainty-aware LLM evaluator named ConfiLM using a human-annotated fine-tuning set and assess ConfiLM’s OOD evaluation ability on a manually designed test set sourced from the 2024 Olympics. Experimental results demonstrate that incorporating uncertainty as additional information during the fine-tuning phase can largely improve the model’s evaluation performance in OOD scenarios. The code and data are released at: https://***/hasakiXie123/LLM-Evaluator-Uncertainty. © 2025, CC BY-NC-SA.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate Unified Anomaly Segmentation

Towards Accurate Unified Anomaly Segmentation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Wenxin Ma Qingsong Yao Xiang Zhang Zhelong Huang Zihang Jiang S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) USTC Suzhou Institute for Advance Research Suzhou Jiangsu China Stanford University Palo Alto California United State School of Medicine Shanghai University Shanghai China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Unsupervised anomaly detection (UAD) from images strives to model normal data distributions, creating discriminative representations to distinguish and precisely localize anomalies. Despite recent advancements in the efficient and unified one-for-all scheme, challenges persist in accurately segmenting anomalies for further monitoring. Moreover, this problem is obscured by the widely-used AUROC metric under imbalanced UAD settings. This motivates us to emphasize the significance of precise segmentation of anomaly pixels using pAP and DSC as metrics. To address the unsolved segmentation task, we introduce the Unified Anomaly Segmentation (UniAS). UniAS presents a multi-level hybrid pipeline that progressively enhances normal information from coarse to fine, incorporating a novel multi-granularity gated CNN (MGG-CNN) into Transformer layers to explicitly aggregate local details from different granularities. UniAS achieves state-of-the-art anomaly segmentation performance, attaining 65.12/59.33 and 40.06/32.50 in pAP/DSC on the MVTec-AD and VisA datasets, respectively, surpassing previous methods significantly. The codes are shared at https://***/Mwxinnn/UniAS.

关键词： Measurement Image segmentation Computer vision Codes Pipelines Logic gates Transformers Data models Monitoring Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Sequence-Aware Online Container Scheduling with Reinforcement Learning in Parked Vehicle Edge computing

引用

IEEE Transactions on Vehicular technology 2025年

作者： Wu, Jianqiu Guo, Jianxiong Tang, Zhiqing Luo, Chuanwen Wang, Tian Jia, Weijia Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Zhuhai519087 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing100083 China

intelligent vehicles, often parked for long periods, are ideally suited to serve as computational nodes to expand the Mobile Edge computing (MEC) infrastructure, with containerization significantly enhancing the system's load balancing, self-healing, resource isolation, and security. However, fluctuations in task demand and frequent container image downloads during peak hours create high loads on containerized nodes, as multiple mobile devices offload tasks simultaneously, leading to significant processing delays. Many existing studies make the simplified assumption of predefined patterns of task arrivals, which overlooks this issue and makes suboptimal decisions. In this paper, we consider a Parked Vehicles (PVs)-extended MEC scenario, where multiple devices request services on PVs functioning as edge servers, all controlled by a central base station. Task arrivals follow observed patterns based on long-term trends, such as peak and off-peak periods, resembling realistic arrival patterns rather than predefined ones. To optimize task offloading by identifying these patterns, we propose the Sequence-Aware Task Scheduling (SATS) algorithm, which is a policy gradient-based deep reinforcement learning approach that integrates Transformer and LSTM architectures to capture patterns in time-series task arrivals and relationships between nodes in a collab.rative and containerized environment, thereby enhancing the efficiency of online task scheduling. The primary objective of SATS is to optimize the task offloading policy and minimize delay and energy consumption for all devices and PVs. Extensive numerical comparisons against baselines demonstrate the effectiveness and advantages of our algorithm. © 1967-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Learning Comprehensive Representation via Selective Activation and Dual-Level Orthogonality for Pedestrian Attribute Recognition

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wu, Junyi Huang, Yan Gao, Min Niu, Yuzhen Chen, Yuzhong Wu, Qiang Zhao, Jianqiang Ministry of Education Engineering Research Center of Big Data Intelligence China Ai Research Center Sdic Intelligence Xiamen Information Co. Ltd Xiamen China Xiamen Meiya Pico Information Security Research Institute Co. Ltd Xiamen China Institute of Automation Beijing China Fuzhou University Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou China University of Technology Sydney School of Electrical and Data Engineering Ultimo Australia

Multi-lab.l Pedestrian Attribute Recognition (PAR) involves identifying a series of semantic attributes in person images. Existing PAR solutions typically rely on CNN as the backbone network to extract pedestrian features. Unfortunately, CNNs process only one adjacent region at a time, resulting in the disappearance of long-range relations between different attribute-specific regions. To address this limitation, we adopt the Vision Transformer (ViT) instead of CNN as the backbone for PAR, aiming to build long-range relations and extract more robust features. However, PAR suffers from an inherent attribute imbalance issue, causing ViT to naturally focus more on attributes that appear frequently in the training set and ignore some pedestrian attributes that appear less. The native features extracted by ViT are not able to tolerate the imbalance attribute distribution issue. To tackle this issue, we propose a novel component and a dual-level loss: the Selective Feature Activation Method (SFAM), the Orthogonal Feature Activation Loss (OFALoss), and Orthogonal Weight Regularization Loss (OWRLoss). SFAM smartly suppresses the more informative attribute-specific features, thus compelling the PAR model to pay greater attention to attribute-specific regions that are often overlooked. The proposed OFALoss enforces an orthogonal constraint on the original feature extracted by ViT and the suppressed features from SFAM, promoting the comprehensiveness of feature representation in each attribute-specific region. Furthermore, OWRLoss is employed for decreasing correlations among entries of the last shared classification layer, which can alleviate the highly correlated of weight vectors caused by non-uniform distribution. This can prevent excessive mutual interference among different attributes during attribute recognition. Our model-agnostic approach is plug-and-play, requiring no additional training parameters in the training process. We conduct experiments on several benchmark P

关键词： Dual-Level Orthogonal Regularization Pedestrian Attribute Recognition Selective Feature Activation

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Access Control with Privacy-Preserving Data Retrieval for Cloud-Assisted IoV

引用

IEEE Transactions on Vehicular technology 2025年

作者： Li, Wenchao Xia, Chunhe Yang, Simiao Wang, Kangming Huang, Guotao Huang, Luqi Guo, Fuchun Susilo, Willy Wang, Tianbo Beihang University School of Cyber Science and Technology Beijing100191 China University of Wollongong School of Computing and Information Technology Institute of Cybersecurity and Cryptology WollongongNSW2522 Australia Beihang University Beijing Key Laboratory of Network Technology Beijing100191 China Guangxi Normal University Guangxi Collab. Innovation Center of Multi-source Information Integration and Intelligent Processing Guilin541004 China Beihang University Sino-French Engineer School Beijing100191 China Beihang University Computer Science and Engineering School Beijing100191 China

In addition to the autonomous driving technology of single vehicles, the inter-group control algorithm serving the data sharing of multi-vehicle cooperative driving has also attracted widespread attention. To ensure secure communication, many encryption schemes have been proposed to protect the interaction data between vehicles. Nevertheless, traditional public key encryption schemes hinder the sharing of encrypted data. Based on the premise of ensuring the confidentiality of encrypted information, in order to facilitate efficient data sharing, conduct data searches across extensive cloud-based datasets, and authorize access under specified conditions, we introduce Fine-Grained Access Control with Privacy-Preserving Data Retrieval (FGAC-PPDR) for the Internet of Vehicles. This scheme offers a secure, flexible, and privacy-centric approach to data sharing for groups of vehicles in the IoV. Our proposed scheme enables encrypted data to be retrieved at the group level by the cloud server, and prevents vehicles outside the group from performing equality tests on the ciphertext. Furthermore, the data owner can create an authorization token with defined conditions to specify how the data is shared. During the process of data search and sharing, intensive computing tasks are undertaken by cloud servers with abundant computational resources. We also demonstrate that our scheme is secure against chosen ciphertext attacks (CCA). Finally, we provide security and performance analyses that verify the feasibility and effectiveness of our proposal. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

UV-activated TiO2 nanoparticles for sensitively detecting ppb-level dimethyl sulfide at room temperature

引用

Sensors and Actuators B: Chemical 2025年 441卷

作者： Rong, Dandan Meng, Gang Mi, Longqing Li, Meng Zhang, Ruofan Ji, Xiaohua Dai, Tiantian Li, Hongtao Fang, Xiaodong You, Libing Deng, Zanhong Anhui Provincial Key Laboratory of Photonic Devices and Materials Anhui Institute of Optics and Fine Mechanics and Key Lab of Photovoltaic and Energy Conservation Materials Chinese Academy of Sciences Hefei230031 China University of Science and Technology of China Hefei230026 China Mozi Laboratory Zhengzhou450000 China School of Information and Artificial Intelligence Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Anhui Agricultural University Hefei230036 China School of Physics and Optoelectronic Engineering Key Laboratory of Opto-Electronic Information Acquisition and Manipulation of Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China College of New Materials and New Energies Shenzhen Technology University Shenzhen518118 China

Dimethyl sulfide (DMS) is one kind of volatile sulfur compounds (VSCs) possessing disagreeable odor, with a low olfactory threshold around 20 ppb. Highly sensitive detection of DMS at room temperature (RT) is critically needed for emerging application with low power consumption, but it remains a significant challenge owing to its low reactivity. Herein, UV photoactivated titanium dioxide (TiO2) nanoparticles (NPs) have been employed for detecting DMS at RT. An eco-friendly ultrasonic crushing solution spray technique was developed to prepare TiO2 based sensors. An ultrahigh response of 30–500 ppb DMS and a low experimental limit of detection (Ra/Rg = 2.7@50 ppb) could be achieved at RT under UV light activation. This work opens a new avenue to achieve highly sensitive, energy-efficient sensors for trace VSCs detection at RT in ambient odor monitoring. © 2025 Elsevier B.V.

关键词： Sulfur dioxide

来源：评论

学校读者我要写书评

暂无评论

A Survey of Commonsense Knowledge Acquisition

引用

Journal of Computer Science & technology 2013年第4期28卷 689-719页

作者：臧良俊曹聪曹亚男吴昱明曹存根 Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences University of the Chinese Academy of Sciences The Second Lab Institute of Information Engineering Chinese Academy of Sciences

Collecting massive commonsense knowledge （CSK） for commonsense reasoning has been a long time standing challenge within artificial intelligence research. Numerous methods and systems for acquiring CSK have been developed to overcome the knowledge acquisition bottleneck. Although some specific commonsense reasoning tasks have been presented to allow researchers to measure and compare the performance of their CSK systems, we compare them at a higher level from the following aspects： CSK acquisition task （what CSK is acquired from where）, technique used （how can CSK be acquired）, and CSK evaluation methods （how to evaluate the acquired CSK）. In this survey, we first present a categorization of CSK acquisition systems and the great challenges in the field. Then, we review and compare the CSK acquisition systems in detail. Finally, we conclude the current progress in this field and explore some promising future research issues.

关键词： commonsense knowledge knowledge acquisition knowledge representation and reasoning

来源：评论

学校读者我要写书评

暂无评论

Primal least squares twin support vector regression

引用

Journal of Zhejiang University-Science C(Computers and Electronics) 2013年第9期14卷 722-732页

作者： Hua-juan HUANG Shi-fei DING Zhong-zhi SHI School of Computer Science and Technology China University of Mining and Technology Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences

The training algorithm of classical twin support vector regression (TSVR) can be attributed to the solution of a pair of quadratic programming problems (QPPs) with inequality constraints in the dual ***,this solution is affected by time and memory constraints when dealing with large *** this paper,we present a least squares version for TSVR in the primal space,termed primal least squares TSVR (PLSTSVR).By introducing the least squares method,the inequality constraints of TSVR are transformed into equality ***,we attempt to directly solve the two QPPs with equality constraints in the primal space instead of the dual space;thus,we need only to solve two systems of linear equations instead of two *** results on artificial and benchmark datasets show that PLSTSVR has comparable accuracy to TSVR but with considerably less computational *** further investigate its validity in predicting the opening price of stock.

关键词： Twin support vector regression Least squares method Primal space Stock prediction

来源：评论

学校读者我要写书评

暂无评论

Semantic-driven management and search for resources in research community

Semantic-driven management and search for resources in resea...

引用

2006 2nd International Conference on Semantics Knowledge and Grid, SKG

作者： Junsheng, Zhang Zhixian, Yan Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)0769532055

In recent years, semantic search has become one hot motivation of the semantic web. In this paper, we propose a semantic-based resource management and search architecture and its implementation in research community, including most of the research relevant resources. We have built two authoring tools respectively for concepts and instances. With the authoring tools, semantic search portal is provided, which has three different interfaces, respectively for retrieval of concept, instance and semantic relationship. Compared with the traditional search methods, semantic search methodology not only gives us more interesting and satisfying search results, whose precision is higher than those of traditional ones only based on keywords, but also displays the results in a more structural and semantic way. © 2006 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RGB-D Hand-Held Object Recognition Based on Heterogeneous Feature Fusion

引用

Journal of Computer Science & technology 2015年第2期30卷 340-352页

作者：吕雄蒋树强 Luis Herranz 王双 Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

Object recognition has many applications in human-machine interaction and multimedia retrieval. However, due to large intra-class variability and inter-class similarity, accurate recognition relying only on RGB data is still a big challenge. Recently, with the emergence of inexpensive RGB-D devices, this challenge can be better addressed by leveraging additional depth information. A very special yet important case of object recognition is hand-held object recognition, as manipulating objects with hands is common and intuitive in human-human and human-machine interactions. In this paper, we study this problem and introduce an effective framework to address it. This framework first detects and segments the hand-held object by exploiting skeleton information combined with depth information. In the object recognition stage, this work exploits heterogeneous features extracted from different modalities and fuses them to improve the recognition accuracy. In particular, we incorporate handcrafted and deep learned features and study several multi-step fusion variants. Experimental evaluations validate the effectiveness of the proposed method.

关键词： RGB-D hand-held object recognition heterogeneous features fusion

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：