检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zheng Chang Shuchen Weng Peixuan Zhang Yu Li Si Li Boxin Shi School of Artificial Intelligence Beijing University of Posts and Telecommunications National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University International Digital Economy Academy

Language-based colorization produces plausible colors consistent with the language description provided by the user. Recent studies introduce additional annotation to prevent color-object coupling and mismatch issues, but they still have difficulty in distinguishing instances corresponding to the same object words. In this paper, we propose a transformer-based framework to automatically aggregate similar image patches and achieve instance awareness without any additional knowledge. By applying our presented luminance augmentation and counter-color loss to break down the statistical correlation between luminance and color words, our model is driven to synthesize colors with better descriptive consistency. We further collect a dataset to provide distinctive visual characteristics and detailed language descriptions for multiple instances in the same image. Extensive experiments demonstrate our advantages of synthesizing visually pleasing and description-consistent results of instance-aware colorization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of vector OFDM with linear MMSE receiver

Performance analysis of vector OFDM with linear MMSE receive...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Yabo Li Ibo Ngebani Xiang-Gen Xia Anders Høst-Madsen Department of Information Science and Electrical Engineering Provincial Key Laboratory of Information Network Technology University of Zhejiang Hangzhou Zhejiang China Department of Electrical and Computer Engineering University of Delaware Newark DE USA Department of Electrical Engineering University of Hawaii Manoa Honolulu HI USA

Vector OFDM (V-OFDM) for single transmit antenna systems is a general transmission scheme in which OFDM and Single-Carrier Frequency Domain Equalization (SC-FDE) can be considered as two extreme/special cases. Due to its flexibility, it has attracted more and more attention recently. So far all studies about V-OFDM assume the Maximum Likelihood (ML) receiver. In this paper, we investigate the performance of V-OFDM with linear Minimum Mean Square Error (MMSE) receiver. We first show that for linear MMSE receiver, all the vector blocks (VB) in V-OFDM have equal performance, this is different from V-OFDM with ML receiver, where different VBs may have different performances. Then, we analyze the diversity order of V-OFDM with linear MMSE receiver, and show that, regardless of the V-OFDM symbol length N, the diversity order can be represented as min{[M2 _ R ], D} + 1, where M is the VB size, R is the spectrum efficiency in bits/symbol, and D is the maximum delay of the multipath channel.

关键词： Receivers Vectors Signal to noise ratio Diversity reception Peak to average power ratio Educational institutions

来源：评论

学校读者我要写书评

暂无评论

L-CAD: language-based colorization with any-level descriptions using diffusion priors 23

L-CAD: language-based colorization with any-level descriptio...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Zheng Chang Shuchen Weng Peixuan Zhang Yu Li Si Li Boxin Shi School of Artificial Intelligence Beijing University of Posts and Telecommunications National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University and National Engineering Research Center of Visual Technology School of Computer Science Peking University International Digital Economy Academy

Language-based colorization produces plausible and visually pleasing colors under the guidance of user-friendly natural language descriptions. Previous methods implicitly assume that users provide comprehensive color descriptions for most of the objects in the image, which leads to suboptimal performance. In this paper, we propose a unified model to perform language-based colorization with any- level descriptions. We leverage the pretrained cross-modality generative model for its robust language understanding and rich color priors to handle the inherent ambiguity of any-level descriptions. We further design modules to align with input conditions to preserve local spatial structures and prevent the ghosting effect. With the proposed novel sampling strategy, our model achieves instance-aware colorization in diverse and complex scenarios. Extensive experimental results demonstrate our advantages of effectively handling any-level descriptions and outperforming both language-based and automatic colorization methods. The code and pretrained models are available at: https://***/changzheng123/L-CAD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Chest X-ray Classification: A Fusion of Topological Data Analysis and ResNet

Contrastive Learning for Chest X-ray Classification: A Fusio...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Hao Ren Zeyu Luo Fengshi Jing Xinyue Zhang Han He Yonghao Yu Dawei Zhao Faculty of Data Science City University of Macau China Minzu University of China Beijing 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) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Lung diseases such as pneumonia and tuberculosis present significant global health challenges, leading to millions of deaths annually. Chest X-ray imaging is crucial for diagnosing these conditions, but interpretation often relies on specialized radiologists, creating barriers in resource-limited areas. This study introduces a novel framework integrating topological data analysis (TDA), deep learning with ResNet-50, and contrastive learning to enhance the accuracy and computational efficiency of chest X-ray analysis. TDA captures global topological structures, while ResNet-50 extracts detailed local features. Contrastive learning then optimizes the feature space, enhancing the model’s discriminative power and generalization capabilities. Comprehensive evaluations on multiple datasets demonstrate the framework’s robustness and effectiveness, showing substantial improvements in diagnostic performance and computational efficiency. These findings suggest that the proposed approach is well-suited for real-time clinical applications, especially in resource-limited settings. Future work will focus on further optimizing the model and exploring its application to other medical imaging modalities, broadening its clinical utility.

关键词： Deep learning Accuracy Computational modeling Contrastive learning Feature extraction Robustness Real-time systems Computational efficiency X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

imiRTP: An Integrated Method to Identifying miRNA-target Interactions in Arabidopsis thaliana

imiRTP: An Integrated Method to Identifying miRNA-target Int...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiandong Ding Shusi Yu Uwe Ohler Jihong Guan Shuigeng Zhou Shanghai Key Laboratory of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Institute for Genome Sciences & Policy and Department of Biostatistics & Bioinformatics Duke University Durham NC USA Department of Computer Science & Technology Tongji University Shanghai China

MiRNA are about 22nt long small noncoding RNAs that post transcriptionally regulate gene expression in animals, plants and protozoa. Confident identification of MiRNA-Target Interactions (MTI) is vital to understand their function. Currently, several integrated programs and databases are available for animal miRNAs, the mechanisms of which are significantly different from plant miRNAs. Here we present imiRTP, an integrated MTI prediction and analysis toolkit for Arabidopsis thaliana. It features two important functions: (i) combination of several effective plant miRNA target prediction methods provides a sufficiently large MTI candidate set, and (ii) different filters allow for an efficient selection of potential targets. The modularity of imiRTP enables the prediction of high quality targets on genome-wide scale.

关键词： Bioinformatics RNA Animals Genomics Databases Prediction methods Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Anomaly-Free Prior Guided Knowledge Distillation for Industrial Anomaly Detection

Anomaly-Free Prior Guided Knowledge Distillation for Industr...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Gang Li Tianjiao Chen Min Li Delong Han MingLe Zhou 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) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Faculty of Data Science City University of Macau Macau China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In industrial manufacturing, visual anomaly detection is critical for maintaining product quality by detecting and preventing production anomalies. Anomaly detection methods based on knowledge distillation demonstrate promising performance in addressing the unpredictability and diversity of anomalies. However, they suffer from a lack of effective guidance from anomaly-free priors when handling anomalous features and underutilize multi-scale features during the segmentation scoring stage, yielding suboptimal detection results. To alleviate these issues, we propose an Anomaly-free Prior Guided knowledge distillation (APG) for industrial anomaly detection. Firstly, it filters the abnormal features by training the de-noising target network with knowledge distillation structure. Concurrently, we propose the Prior Perception Propagation Module (P 3 M), which extracts more efficient anomaly-free features by imposing constraints on anomalous features. Secondly, we propose the Multi-scale Prior Guided Fusion Module (MPGFM) to improve anomaly detection accuracy by utilizing anomaly-free features from the target network as priors to guide the generation and fusion of cross-scale differential features. Finally, the Global Perception Enhancement Module (GPEM) is proposed to construct an anomaly scoring network, leveraging comprehensive scene features to enhance the detection and localization performance of numerous small-target anomalies in industrial manufacturing. Extensive experiments on the MVTecAD and BTAD datasets show that the proposed method demonstrates a consistent and significant outperformance against competing methods.

关键词： Training Location awareness Visualization Noise reduction Production Feature extraction Product design Manufacturing Quality assessment Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Short-Term Electric Load Forecasting Method Based on the Fusion of Global and Local Features

A Short-Term Electric Load Forecasting Method Based on the F...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Haozhan Gu Hangwei Tian Jingchun Wang Yumei Li Shandong University Of Arts Academy of Fine Arts China 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) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Accurate short-term electric load forecasting is crucial for ensuring the stability and efficiency of the power grid. This study proposes an innovative dual-branch electric load forecasting model that enhances the accuracy of predictions by processing global and local features in parallel. Global features are extracted through the Savitzky-Golay filter and a linear model to capture the overall trends of the load data. Local features are identified using the Convolutional Self-Attention Module, which integrates the local perception capabilities of Convolutional neural network with the self-attention mechanism of Transformers. By employing a Weighted Feature Fusion Network, we effectively integrate global and local information to enhance the performance of load forecasting. Experimental results demonstrate that the proposed model significantly outperforms existing models in predictive performance. The model presented in this study offers a new perspective on electric load forecasting and has the potential to become an effective tool for power system planning and scheduling.

关键词： Accuracy Load forecasting Electricity Nonlinear filters Predictive models Power system stability Feature extraction Transformers Data models Load modeling

来源：评论

学校读者我要写书评

暂无评论

LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation

arXiv

引用

arXiv 2024年

作者： Hong, Lingyi Liu, Zhongying Chen, Wenchao Tan, Chenzhi Feng, Yuang Zhou, Xinyu Guo, Pinxue Li, Jinglun Chen, Zhaoyu Gao, Shuyong Zhang, Wei Zhang, Wenqiang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Shanghai Engineering Research Center of AI&Robotics Academy for Engineering&Technology Fudan University Shanghai China Engineering Research Center of AI&Robotics Ministry of Education Academy for Engineering&Technology Fudan University Shanghai China The Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchmarks mainly focus on short-term videos lasting about 5 seconds, where objects remain visible most of the time. However, these benchmarks poorly represent practical applications, and the absence of long-term datasets restricts further investigation of VOS in realistic scenarios. Thus, we propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average, approximately 5 times longer than videos in existing datasets. Each video includes various attributes, especially challenges deriving from the wild, such as long-term reappearing and cross-temporal similar objects. Compared to previous benchmarks, our LVOS better reflects VOS models' performance in real scenarios. Based on LVOS, we evaluate 20 existing VOS models under 4 different settings and conduct a comprehensive analysis. On LVOS, these models suffer a large performance drop, highlighting the challenge of achieving precise tracking and segmentation in real-world scenarios. Attribute-based analysis indicates that key factor to accuracy decline is the increased video length, emphasizing LVOS's crucial role. We hope our LVOS can advance development of VOS in real scenes. Data and code are available at https://***/lvos. ***/. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Modeling for Improving Prediction of Toxicity

Uncertainty-Aware Modeling for Improving Prediction of Toxic...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Xinlei Zhou Xizhao Wang Xinpeng Zhou Siwu Tu Ranwang School of Mathematical Sciences Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China College of Electronic Information Guangxi Minzu University 530000 China Jiangxi Drug Inspection Center Nanchang China

ISBN: (数字)9798331528041

ISBN: (纸本)9798331528058

Accurately predicting molecular toxicity is challenging in drug discovery and chemical safety assessment. Except for the representation of molecular structure, the inherent class imbalance and uncertainty often complicate the task. In this work, we present UnBGMT (Uncertainty-Aware Balanced Graph Multi-set Transformer), which integrates uncertainty modeling into the Graph Multiset Transformer (GMT) framework to improve the reliability and accuracy of molecular toxicity predictions. Our method employs Monte Carlo dropout (MC dropout) to evaluate uncertainty, which is then used to guide an adaptive loss function that adjusts weights in training. This approach guides the model to focus on the minority and samples with middle-level uncer-tainty, mitigating issues related to class imbalance and improving model stability. We conducted sufficient experiments on the Tox21 dataset, demonstrating the superiority of UnBGMT by comparing performance with baseline models and conducting ablation studies. Our results highlight the benefits of incorporating uncertainty in toxicity prediction, which provides a deeper insight into the im-pact of uncertainty on model performance.

关键词： Adaptation models Uncertainty Toxicology Molecular communication Predictive models Transformers Stability analysis Safety Drug discovery Chemicals

来源：评论

学校读者我要写书评

暂无评论

User Behavior-Based Collaborative Filtering Recommendation Algorithm and Visualization in Second-Hand Trading Platform

User Behavior-Based Collaborative Filtering Recommendation A...

引用

Sensors, Electronics and computer Engineering (ICSECE), IEEE International Conference on

作者： Rui Qiao Xin Wang Xiaoben Zhong School of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan Hubei China Yunnan College of Business Management Anning China

ISBN: (数字)9798350373646

ISBN: (纸本)9798350373653

In the backdrop of the digital era, the demand for second-hand trading within campuses has seen a significant rise. This project aims at designing a second-hand trading platform that merges the latest technological trends, providing a secure and convenient trading environment for students. The system utilizes Spring Boot for backend development and Vue along with ElementUI for constructing the user interface, ensuring efficient operation and enhancing user interaction experience. The server employs Spring Boot's built-in Tomcat, simplifying the deployment process. For data persistence, Mybatis framework is used for flexible and efficient interactions with the MySQL database. The platform introduces a collaborative filtering algorithm based on user behavior for smart product recommendations, further improving the user experience. The system integrates core modules such as user management, product browsing, shopping cart functionalities, and order processing, innovatively introducing an offline transaction confirmation mechanism to ensure transaction security and reliability while avoiding legal risks associated with online payments. With its B/S architecture, the platform operates more smoothly, making it more accessible to users. Experimental results demonstrate that the platform has a user-friendly interface and efficient data processing capabilities, receiving widespread recognition and praise from users, proving its practicality and innovativeness.

关键词： Law Collaborative filtering Market research User experience Sensor systems Servers Security Reliability Springs Intelligent sensors

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：