检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Fang, Sheng Li, Kaiyu Li, Zhe Zhao, Jianli Zhang, Xingli College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China School of Software Engineering Xi’an Jiaotong University Xi’an710049 China

Image translation for change detection or classification in bi-temporal remote sensing images is unique. Although it can acquire paired images, it is still unsupervised. Moreover, strict semantic preservation in translation is always needed instead of multimodal outputs. In response to these problems, this paper proposes a new method, SRUIT (Semantically Robust Unsupervised Image-to-image Translation), which ensures semantically robust translation and produces deterministic output. Inspired by previous works, the method explores the underlying characteristics of bi-temporal Remote Sensing images and designs the corresponding networks. Firstly, we assume that bi-temporal Remote Sensing images share the same latent space, for they are always acquired from the same land location. So SRUIT makes the generators share their high-level layers, and this constraint will compel two domain mapping to fall into the same latent space. Secondly, considering land covers of bi-temporal images could evolve into each other, SRUIT exploits the cross-cycle-consistent adversarial networks to translate from one to the other and recover them. Experimental results show that constraints of sharing weights and cross-cycle consistency enable translated images with both good perceptual image quality and semantic preservation for significant differences. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

QCACNN: A Quantum Convolutional Neural Network Algorithm for Traffic Sign Recognition in Carbon-Intelligent Electric Vehicles

引用

IEEE Internet of Things Journal 2025年

作者： Qu, Zhiguo Xia, Yichen Sun, Le Liu, Wenjie Muhammad, Ghulam Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education School of Computer Science Nanjing210044 China Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Nanjing University of Information Science and Technology School of Software Nanjing210044 China King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh Saudi Arabia

Traffic sign recognition is essential for autonomous driving, enhancing driving efficiency and ensuring road safety. Traffic signs utilize colors and patterns to relay critical information, with color accuracy being especially significant. Traditional models, reliant on extensive data and computing resources, struggle to meet the efficiency demands of electric vehicles with carbon-intelligent computing. Leveraging the physical properties of quantum superposition states, quantum computing offers a solution with its unique parallel computing capabilities, potentially enhancing recognition efficiency and facilitating real-time processing. Quantum Convolutional Neural Networks (QCNNs) show promise in processing large-scale image data with improved efficiency and accuracy. However, most of QCNN researches focus on grayscale image classification, with limited studies on multi-channel data. This paper introduces the Quantum Channel Attention Convolutional Neural Network (QCACNN), which incorporates a Quantum Channel Attention Layer (QCAL) to enhance multi-channel data classification. The experimental results demonstrate that QCACNNs surpasses traditional QCNNs in traffic sign recognition, performing comparably to conventional CNNs and SENet models with fewer computing resources. Detailed performance analysis and ablation studies validate the effectiveness of each component within this architecture. Quantum noise resistance tests confirm the robustness of QCACNN, making it a viable solution for electric vehicles with enhanced scalability. © 2014 IEEE.

关键词： Quantum channel

来源：评论

学校读者我要写书评

暂无评论

Robust ANN Searching for Dynamic Vector Streams without Rebuilding Index

Robust ANN Searching for Dynamic Vector Streams without Rebu...

引用

computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Haowen Bian Lingwei Chao Jingxuan Su Wenhong Tian Ruini Xue School of Computer Science and Engineering (School of Cyber Security) University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

Graph-based approximate nearest neighbour (ANN) algorithms have dominated vector indexing recently. However, some of them do not support incremental vector addition, while most of them do not support in-place deletion. Therefore, additional rebuilding overhead is required to keep the index updated. We propose HSG (Hybrid Stride Graph) to enable the vector index to accept dynamic vector streams. Inspired by the K-ANN graph and NSG, HSG constructs the index with short and long edges simultaneously without any preprocessing or prior dataset knowledge. Finally, HSG is evaluated against three well-known datasets and the experimental results indicate that HSG can deliver acceptable QPS with an excellent recall guarantee.

关键词： Heuristic algorithms Big Data Approximation algorithms Vectors Indexes Artificial intelligence Streams Indexing

来源：评论

学校读者我要写书评

暂无评论

‘Skimming-Perusal’ Detection: A Simple Object Detection Baseline in GigaPixel-level Images

‘Skimming-Perusal’ Detection: A Simple Object Detection Ba...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhibin Zhang Wanli Xue Kaihua Zhang Shengyong Chen School of Computer Science and Engineering Tianjin University of Technology China School of Computer and Software Nanjing University of Information Science and Technology China

Object detection has achieved amazing performance in regular-sized images, but with the emergence of gigapixel-level images, even the most advanced object detection methods cannot be directly used to process them quickly and efficiently. Therefore, this paper proposes a simple baseline for gigapixel-level images object detection called Skimming-Perusal Detection (SPDet). The SPDet consists mainly of two parts, a skimming model and a perusal model. The skimming model is based on an efficient global-to-local search strategy to detect possible regions containing objects. Non-object regions are merged through a skimming iterative merging strategy to generate skimming patch candidates. The perusal model adaptive scales the skimming patch candidates guided by the coarse detection of the skimming model. Extensive evaluations on the PANDA dataset demonstrate that the SPDet boosts detection speed on gigapixel-level images by 6× while achieving better performance than a variety of state-of-the-art methods. The source code is released at https://***/TJUT-CV/SPDet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints

arXiv

引用

arXiv 2025年

作者： Gao, Yansong Peng, Huaibing Ma, Hua Dai, Zhiyang Wang, Shuo Hu, Hongsheng Fu, Anmin Xue, Minhui The School of Computer Science and Software Engineering The University of Western Australia Australia The School of Computer Science and Engineering Nanjing University of Science and Technology China Data61 CSIRO Australia The School of Cyber Science and Engineering Shanghai Jiao Tong University China The School of Information and Physical Sciences The University of Newcastle Australia

For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the targeted underlying victim models, we present a fresh temporal paradigm for understanding these attacks. Of paramount discovery is that these imprints are encapsulated within a single loss metric, spanning universally across diverse tasks such as classification and regression, and modalities including image, text, and audio. Recognizing the distinct nature of loss between adversarial and clean examples, we exploit this temporal imprint for AE detection by proposing TRAIT (Traceable Adversarial Temporal Trajectory Imprints). TRAIT operates under minimal assumptions without prior knowledge of attacks, thereby framing the detection challenge as a one-class classification problem. However, detecting AEs is still challenged by significant overlaps between the constructed synthetic losses of adversarial and clean examples due to the absence of ground truth for incoming inputs. TRAIT addresses this challenge by converting the synthetic loss into a spectrum signature, using the technique of Fast Fourier Transform to highlight the discrepancies, drawing inspiration from the temporal nature of the imprints, analogous to time-series signals. Across 12 AE attacks including SMACK (USENIX Sec’2023), TRAIT demonstrates consistent outstanding performance across comprehensively evaluated modalities (image, text, audio), tasks (classification and regression), datasets (nine datasets), and model architectures (e.g., ResNeXt50, BERT, RoBERTa, AudioNet). In all scenarios, TRAIT achieves an AE detection accuracy exceeding 97%, often around 99%, while maintaining a false rejection rate of 1%. TRAIT remains effective under the formulated strong adaptive attacks. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Retrieval Augmented Generation Systems Using AI Models and Graph Databases

Enhancing Retrieval Augmented Generation Systems Using AI Mo...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Souvik Mukherjee Soosan Shabnam Sara Hasan D. Ajitha Department of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Software Systems School of Computer Science and Engineering (SCOPE) Vellore Institute of Technology Vellore Tamil Nadu India

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

This paper outlines the process of generating a Neo4j graph database powered by Language Models (LLMs). The primary goal is to extract structured information from unstructured data, including user profiles, paper briefs, and Slack messages, and convert them into Cypher queries. The data is then ingested into Neo4j to build a graph database that captures relationships between users, paper, technologies, and messages. A pipeline was developed to automate the process, ensuring accurate entity and relationship extraction using predefined templates. This approach allows for efficient data representation and supports consultancy in managing large datasets by generating insightful visualizations and querying capabilities.

关键词： Ciphers Accuracy Databases Pipelines Retrieval augmented generation Loading Data visualization Transforms Paper technology Data mining

来源：评论

学校读者我要写书评

暂无评论

DualVAE: Dual Disentangled Variational AutoEncoder for Recommendation

arXiv

引用

arXiv 2024年

作者： Guo, Zhiqiang Li, Guohui Li, Jianjun Wang, Chaoyang Shi, Si School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China Wuhan Digital Engineering Institute China China

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction data, neglecting to model the diverse matching relationships between users and items behind their interactions, leading to limited performance and weak interpretability. To address this problem, we propose a Dual Disentangled Variational AutoEncoder (DualVAE) for collaborative recommendation, which combines disentangled representation learning with variational inference to facilitate the generation of implicit interaction data. Specifically, we first implement the disentangling concept by unifying an attention-aware dual disentanglement and disentangled variational autoencoder to infer the disentangled latent representations of users and items. Further, to encourage the correspondence and independence of disentangled representations of users and items, we design a neighborhood-enhanced representation constraint with a customized contrastive mechanism to improve the representation quality. Extensive experiments on three real-world benchmarks show that our proposed model significantly outperforms several recent state-of-the-art baselines. Further empirical experimental results also illustrate the interpretability of the disentangled representations learned by DualVAE. Copyright © 2024, The Authors. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Learning to represent code semantics

引用

science CHINA Information sciences 2025年第7期68卷 1-21页

作者： Fang LIU Ge LI Qianhui ZHAO Li ZHANG State Key Laboratory of Complex Critical Software Environment Beijing 100191 China School of Computer Science Engineering Beihang University Beijing 100191 China Key Laboratory of High Confidence Software Technologies Peking University ) Ministry of Education Beijing 100871 China School of Computer Science Peking University Beijing 100871 China

Code semantic learning serves as the basis of many program analysis tasks. Researchers have paid much effort to build robust and effective code representation models over the *** line of work focuses on introducing the code structure into the representations. To further improve the robustness of the code representation, approaches based on compiler intermediate representations (IRs) are proposed. However, these IR-based models suffer from heavy computational costs and memory overhead. How to represent program semantics effectively and efficiently still remains a challenge. To this end, we propose EECS, an effective and efficient code semantic representation approach based on compiler IRs and a hybrid attention mechanism. For input representation, to address the unlimited vocabulary size issue in IR, we propose a variable identification strategy to allocate each register variable to a new ID that can represent their relative positions. Besides, we also extract the data flow information among the code blocks. Then we build a hierarchical multi-layer Transformer encoder to capture the data dependency information as well as the code semantics through a hybrid attention mechanism. To enable EECS to learn code semantics and functionality better, we optimize three objectives jointly during the training process. Experimental results on three code semantic understanding tasks show that EECS performs better than the state-of-the-art techniques, demonstrating the remarkable capability of EECS on program semantics understanding.

关键词： software engineering code semantic learning compiler intermediate representation data dependency modeling artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Enhancing Topic Interpretability for Neural Topic Modeling Through Topic-Wise Contrastive Learning

Enhancing Topic Interpretability for Neural Topic Modeling T...

引用

International Conference on Data engineering

作者： Xin Gao Yang Lin Ruiqing Li Yasha Wang Xu Chu Xinyu Ma Hailong Yu Software Engineering Institution School of Computer Science Peking University Beijing China Key Lab of High Confidence Software Technologies Ministry of Education Beijing China National Engineering Research Center of Software Engineering Peking University Beijing China Center on Frontiers of Computing Studies School of Computer Science Peking University

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Data mining and knowledge discovery are essential aspects of extracting valuable insights from vast datasets. Neural topic models (NTMs) have emerged as a valuable unsupervised tool in this field. However, the predominant objective in NTMs, which aims to discover topics maximizing data likelihood, often lacks alignment with the central goals of data mining and knowledge discovery which is to reveal interpretable insights from large data repositories. Overemphasizing likelihood maximization without incorporating topic regularization can lead to an overly expansive latent space for topic modeling. In this paper, we present an innovative approach to NTMs that addresses this misalignment by introducing contrastive learning measures to assess topic interpretability. We propose a novel NTM framework, named ContraTopic, that integrates a differentiable regularizer capable of evaluating multiple facets of topic interpretability throughout the training process. Our regularizer adopts a unique topic-wise contrastive methodology, fostering both internal coherence within topics and clear external distinctions among them. Comprehensive experiments conducted on three diverse datasets demonstrate that our approach consistently produces topics with superior interpretability compared to state-of-the-art NTMs.

关键词： Training Measurement Contrastive learning Coherence Knowledge discovery Data engineering Data models

来源：评论

学校读者我要写书评

暂无评论

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories 62

DevEval: A Manually-Annotated Code Generation Benchmark Alig...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Li, Jia Li, Ge Zhao, Yunfei Li, Yongmin Liu, Huanyu Zhu, Hao Wang, Lecheng Liu, Kaibo Fang, Zheng Wang, Lanshen Ding, Jiazheng Zhang, Xuanming Zhu, Yuqi Dong, Yihong Jin, Zhi Li, Binhua Huang, Fei Li, Yongbin Gu, Bin Yang, Mengfei School of Computer Science Peking University China Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education China Alibaba Group China Beijing Institute of Control Engineering China China Academy of Space Technology China

ISBN: (纸本)9798891760998

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. To address the knowledge gap, we propose a new benchmark named DevEval, which has three advances. 1 DevEval aligns with real-world repositories in multiple dimensions, e.g., code and dependency distributions. 2 DevEval is annotated by 13 developers and contains comprehensive annotations (e.g., requirements, original repositories, reference code, and reference dependencies). 3 DevEval comprises 1,825 testing samples from 115 repositories, covering 10 popular domains (e.g., Internet, Database). Based on DevEval, we propose repository-level code generation and evaluate 8 popular LLMs on DevEval (e.g., gpt-4, gpt-3.5, StarCoder 2, DeepSeek Coder, CodeLLaMa). Our experiments reveal these LLMs' coding abilities in real-world code repositories. For example, the highest Pass@1 of gpt-4 only is 53.04% in our experiments. We also analyze LLMs' failed cases and summarize their shortcomings. We hope DevEval can facilitate the development of LLMs in real code repositories. DevEval, prompts, and LLMs' predictions have been released. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：