检索结果-内蒙古大学图书馆

Rethinking attention mechanism for enhanced pedestrian attribute recognition

Neurocomputing 2025年 639卷

作者： Wu, Junyi Huang, Yan Gao, Min Niu, Yuzhen Chen, Yuzhong Wu, Qiang Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fujian Fuzhou350108 China Engineering Research Center of BigData Intelligence Ministry of Education Fujian Fuzhou350108 China Australian Artificial Intelligence Institute University of Technology Sydney SydneyNSW2007 Australia Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fujian Fuzhou350108 China School of Electrical and Data Engineering University of Technology Sydney SydneyNSW2007 Australia

Pedestrian Attribute Recognition (PAR) plays a crucial role in various computer vision applications, demanding precise and reliable identification of attributes from pedestrian images. Traditional PAR methods, though effective in leveraging attention mechanisms, often suffer from the lack of direct supervision on attention, leading to potential overfitting and misallocation. This paper introduces a novel and model-agnostic approach, Attention-Aware Regularization (AAR), which rethinks the attention mechanism by integrating causal reasoning to provide direct supervision of attention maps. AAR employs perturbation techniques and a unique optimization objective to assess and refine attention quality, encouraging the model to prioritize attribute-specific regions. Our method demonstrates significant improvement in PAR performance by mitigating the effects of incorrect attention and fostering a more effective attention mechanism. Experiments on standard datasets showcase the superiority of our approach over existing methods, setting a new benchmark for attention-driven PAR models. © 2025 The Authors

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

AN EMPIRICAL ANALYSIS OF UNCERTAINTY IN LARGE LANGUAGE MODEL EVALUATIONS

arXiv

引用

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

A Semantic Link Network Model for Supporting Traceability of Logistics on Blockchain

arXiv

引用

arXiv 2025年

作者： Sun, Xiaoping Zhuge, Sirui Zhuge, Hai Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China King’s College London United Kingdom Publicis Sapient London United Kingdom Great Bay University Dongguan China Great Bay Institute for Advanced Study Dongguan China

The ability of tracing states of logistic transportations requires an efficient storage and retrieval of the state of logistic transportations and locations of logistic objects. However, the restriction of sharing states and locations of logistic objects across organizations from different countries makes it hard to deploy a centralized database for implementing the traceability in a cross-border logistic system. This paper proposes a semantic data model on Blockchain to represent a logistic process based on the Semantic Link Network model where each semantic link represents a logistic transportation of a logistic object between two parties. A state representation model is designed to represent the states of a logistic transportation with semantic links. It enables the locations of logistic objects to be derived from the link states. A mapping from the semantic links to the blockchain transactions is designed to enable schema of semantic links and states of semantic links to be published in blockchain transactions. To improve the efficiency of tracing a path of semantic links on blockchain platform, an algorithm is designed to build shortcuts along the path of semantic links to enable a query on the path of a logistic object to reach the target in logarithmic steps on the blockchain platform. A reward-penalty policy is designed to allow participants to confirm the state of links on blockchain. Analysis and simulation demonstrate the flexibility, effectiveness and the efficiency of Semantic Link Network on immutable blockchain for implementing logistic traceability. © 2025, CC BY.

关键词：

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

DMFVAE:miRNA-disease associations prediction based on deep matrix factorization method with variational autoencoder

引用

Frontiers of Computer Science 2024年第6期18卷 259-270页

作者： Pijing WEI Qianqian WANG Zhen GAO Ruifen CAO Chunhou ZHENG Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China

MicroRNAs(miRNAs)are closely related to numerous complex human diseases,therefore,exploring miRNA-disease associations(MDAs)can help people gain a better understanding of complex disease *** increasing number of computational methods have been developed to predict ***,the sparsity of the MDAs may hinder the performance of many *** addition,many methods fail to capture the nonlinear relationships of miRNA-disease network and inadequately leverage the features of network and neighbor *** this study,we propose a deep matrix factorization model with variational autoencoder(DMFVAE)to predict potential *** first decomposes the original association matrix and the enhanced association matrix,in which the enhanced association matrix is enhanced by self-adjusting the nearest neighbor method,to obtain sparse vectors and dense vectors,***,the variational encoder is employed to obtain the nonlinear latent vectors of miRNA and disease for the sparse vectors,and meanwhile,node2vec is used to obtain the network structure embedding vectors of miRNA and disease for the dense ***,sample features are acquired by combining the latent vectors and network structure embedding vectors,and the final prediction is implemented by convolutional neural network with channel *** evaluate the performance of DMFVAE,we conduct five-fold cross validation on the HMDD v2.0 and HMDD v3.2 datasets and the results show that DMFVAE performs ***,case studies on lung neoplasms,colon neoplasms,and esophageal neoplasms confirm the ability of DMFVAE in identifying potential miRNAs for human diseases.

关键词： miRNA-disease association deep matrix factorization self-adjusted nearest neighbor variational encoder network structure

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

Sgde-gep: A novel algorithm of gep

Sgde-gep: A novel algorithm of gep

引用

International Conference on Computer Science and Software Engineering, CSSE 2008

作者： Peng, Yu-Zhong Yuan, Chang-An Wang, Yan Qin, Xiao Key Lab of Scientific Computing Intelligent Information processing in Universities of Guangxi Guangxi Teachers Education University Nanning China

ISBN: (纸本)9780769533360

Traditional GEP algorithm takes up many system resources in decoding and evaluating due to the operation of the tree construction and corresponding traversing. This paper aims to introduce a novel GEP algorithm to alleviate the drawback mentioned above. The main contributions include:(1) presenting a new method for decoding and evaluating chromosome (SGDE), and proposing the corresponding ETs construction schema;(2) proving the relative natures of SGDE-GEP;(3)The experiments showed that the average efficiency of SGDE-GEP can be raised from 18.94% to 23.11% compared with the traditional GEP. © 2008 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

VIPLFaceNet： an open source deep face recognition SDK

引用

Frontiers of Computer Science 2017年第2期11卷 208-218页

作者： Xin LIU Meina KAN Wanglong WU Shiguang SHAN Xilin CHEN Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

Robust face representation is imperative to highly accurate face recognition. In this work, we propose an open source face recognition method with deep representation named as VIPLFaceNet, which is a lO-layer deep convolu- tional neural network with seven convolutional layers and three fully-connected layers. Compared with the well-known AlexNet, our VIPLFaceNet takes only 20% training time and 60% testing time, but achieves 40% drop in error rate on the real-world face recognition benchmark LFW. Our VIPLFaceNet achieves 98.60% mean accuracy on LFW us- ing one single network. An open-source C＋＋ SDK based on VIPLFaceNet is released under BSD license. The SDK takes about 150ms to process one face image in a single thread on an i7 desktop CPU. VIPLFaceNet provides a state-of-the-art start point for both academic and industrial face recognition applications.

关键词： deep learning face recognition open source,VIPLFaceNet

来源：评论

学校读者我要写书评

暂无评论

Relation Reconstructive Binarization of word embeddings

引用

Frontiers of Computer Science 2022年第2期16卷 47-54页

作者： Feiyang PAN Shuokai LI Xiang AO Qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Word-embedding acts as one of the backbones of modern natural language processing(NLP).Recently,with the need for deploying NLP models to low-resource devices,there has been a surge of interest to compress word embeddings into hash codes or binary vectors so as to save the storage and memory ***,existing work learns to encode an embedding into a compressed representation from which the original embedding can be *** these methods aim to preserve most information of every individual word,they often fail to retain the relation between words,thus can yield large loss on certain *** this end,this paper presents Relation Reconstructive Binarization(R2B)to transform word embeddings into binary codes that can preserve the relation between *** its heart,R2B trains an auto-encoder to generate binary codes that allow reconstructing the wordby-word relations in the original embedding *** showed that our method achieved significant improvements over previous methods on a number of tasks along with a space-saving of up to 98.4%.Specifically,our method reached even better results on word similarity evaluation than the uncompressed pre-trained embeddings,and was significantly better than previous compression methods that do not consider word relations.

关键词： embedding compression variational auto-encoder binary word embedding

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：