检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Meng, Guanghao Dai, Tao Chen, Bin Li, Naiqi Jiang, Yong Xia, Shu-Tao Tsinghua University Tsinghua Shenzhen International Graduate School China Peng Cheng Laboratory Shenzhen China Shenzhen University College of Computer Science and Software Engineering China Harbin Institute of Technology Department of Computer Science and Technology Shenzhen China

ISBN: (纸本)9781728163277

Deep neural network (DNN) based scene text recognition (STR) methods usually require a large amount of annotated data for training, which is time-consuming and cost-expensive in practice. To address this issue, many data augmentation methods have been developed to train recognizers by improving the diversity of training samples. However, most existing methods neglect the difficulty inherent in samples, and easily suffer from the problem of over-diversity, i.e., the distribution of the augmented data significantly deviates from that of clean data. In this paper, we propose a novel difficulty-aware data augmentation framework for scene text recognition, which jointly considers the difficulty of samples and the strength of augmentations. Specifically, our framework first predicts the sample difficulty, followed by an adaptive data augmentation strategy. Furthermore, we build a more diverse set of augmentation methods for STR and integrate it into our augmentation framework. Extensive experiments on scene text recognition benchmarks show that our augmentation framework significantly improves the performance of recognizers. © 2023 IEEE.

关键词： data augmentation deep neural network difficulty-aware Scene text recognition

来源：评论

学校读者我要写书评

暂无评论

Robust Activity Recognition Based on Human Skeleton for Video Surveillance 9

Robust Activity Recognition Based on Human Skeleton for Vide...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Zhang, Xiang Xie, Lei Bu, Yanling Lin, Zhenjie Wang, Liming Nanjing University State Key Laboratory for Novel Software Technology China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China China Southern Power Grid Digital Platform Technology Company China

ISBN: (纸本)9798350319804

Activity recognition is an important task in video analysis, which can be used in accident monitoring and other daily applications. Traditional activity recognition methods are mainly based on the pixel-level analysis of 2D images. However, they achieve poor robustness in various complex environments, and are vulnerable to the perspective distortion caused by the fixed camera view. To address these challenges, we propose a robust skeleton-based human activity recognition method using a fixed monocular surveillance camera. We encode human skeleton with more critical motion information like pairwise distances between keypoints to capture high-level motion modality. Besides, we normalize skeleton data to eliminate the defects of 2D frames, such as the impact of distance on skeleton scale. Furthermore, we propose a skeleton calibration method based on perspective transformation to adapt our method to the deployment environment of surveillance cameras, especially different downward pitch angles. Experimental results show the recognition accuracy of our system reaches 91 percent with a frame rate of 10 FPS. © 2023 IEEE.

关键词： Activity recognition Human skeleton Surveillance video

来源：评论

学校读者我要写书评

暂无评论

Learning Based Opportunistic Data Transmission for Cognitive IoT 17

Learning Based Opportunistic Data Transmission for Cognitive...

引用

17th IEEE International Conference on Social Computing and Networking, SocialCom 2024

作者： Li, Li Zhong, Xiaoxiong Shenzhen Institute of Information Technology School of Computer Science Shenzhen518172 China Tsinghua Shenzhen International Graduate School Shenzhen518055 China Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software Guilin541004 China

ISBN: (纸本)9798331521097

As the rapid development of communication technology, more and more smart devices will be connected in cognitive radio Internet of Things (CIoT) using an opportunistic manner. However, the dynamicity and heterogeneity of spectrum will make it more difficult in data transmission strategy design for unreliable IoT. Opportunistic routing exploits the broadcast property of wireless medium to improve network performance in an opportunistic communication manner. Inspired by this, in this paper, we propose a Nash-learning and Transfer Learning based Opportunistic Data Transmission scheme, NTLODT, for differentiated services CIoT, which exploits Nash-learning for candidate set optimization and transfer learning for data transmission decision from a trust mechanism perspective. In addition, we prove that the convergence and complexity of the proposed algorithm. The simulation results demonstrate that the effectiveness of NTLODT in terms of average energy cost per bit, average delay, expected cost of routing and throughput. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Context-aware API recommendation using tensor factorization

引用

Science China(Information Sciences) 2023年第2期66卷 78-93页

作者： Yu ZHOU Chen CHEN Yongchao WANG Tingting HAN Taolue CHEN College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics State Key Laboratory for Novel Software Technology Nanjing University Birkbeck University of London

An activity constantly engaged by most programmers in coding is to search for appropriate application programming interfaces(APIs). Contextual information is widely recognized to play a crucial role in effective API recommendation, but it is largely overlooked in practice. In this paper, we propose contextaware API recommendation using tensor factorization(CARTF), a novel API recommendation approach in considering programmers' working context. To this end, we use tensors to explicitly represent the queryAPI-context triadic relation. When a new query is made, CARTF harnesses word embeddings to retrieve similar user queries, based on which a third-order tensor is constructed. CARTF then applies non-negative tensor factorization to complete missing values in the tensor and the Smith-Waterman algorithm to identify the most matched context. Finally, the ranking of the candidate APIs can be derived based on which API sequences are recommended. Our evaluation confirms the effectiveness of CARTF for class-level and method-level API recommendations, outperforming state-of-the-art baseline approaches against a number of performance metrics, including SuccessRate, Precision, and Recall.

关键词： API recommendation tensor factorization context awareness word embedding intelligent software development

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Models 35

Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Mode...

引用

35th IEEE International Symposium on software Reliability Engineering Workshops, ISSREW 2024

作者： Zhang, Shenglin Zhu, Pengtian Ma, Minghua Wang, Jiagang Sun, Yongqian Li, Dongwen Wang, Jingyu Guo, Qianying Hua, Xiaolei Zhu, Lin Pei, Dan Nankai University China Haihe Laboratory of Information Technology Application Innovation China Microsoft Tsinghua University China Tianjin Key Laboratory of Software Experience and Human Computer Interaction China China Mobile Research Institute China Beijing National Research Center for Information Science and Technology China

ISBN: (纸本)9798350367041

Large language models (LLMs) excel at general question-answering (Q&A) but often fall short in specialized domains due to a lack of domain-specific knowledge. Commercial companies face the dual challenges of privacy protection and resource constraints when involving LLMs for fine-tuning. This paper propose a novel framework, Self-Evolution, designed to address these issues by leveraging lightweight open-source LLMs through multiple iterative fine-tuning rounds. To enhance the efficiency of iterative fine-tuning, Self-Evolution employ a strategy that filters and reinforces the knowledge with higher value during the iterative process. We employed Self-Evolution on Qwen1.5-7B-Chat using 4,000 documents containing rich domain knowledge from China Mobile, achieving a performance score 174% higher on domain-specific question-answering evaluations than Qwen1.5-7B-Chat and even 22% higher than Qwen1.5-72B-Chat. Self-Evolution has been deployed in China Mobile's daily operation and maintenance for 117 days, and it improves the efficiency of locating alarms, fixing problems, and finding related reports, with an average efficiency improvement of over 18.6%. In addition, we release Self-Evolution framework code in https://***/Zero-Pointer/Self-Evolution. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Mean estimation over numeric data with personalized local differential privacy

引用

Frontiers of computer Science 2022年第3期16卷 183-192页

作者： Qiao XUE Youwen ZHU Jian WANG College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic TechnologyGuilin 541004China School of Cyber Security Gansu University of Political Science and LawLanzhou 730070China

The fast development of the Internet and mobile devices results in a crowdsensing business model,where individuals(users)are willing to contribute their data to help the institution(data collector)analyze and release useful ***,the reveal of personal data will bring huge privacy threats to users,which will impede the wide application of the crowdsensing *** settle the problem,the definition of local differential privacy(LDP)is ***,to respond to the varied privacy preference of users,resear-chers propose a new model,i.e.,personalized local differential privacy(PLDP),which allow users to specify their own privacy *** this paper,we focus on a basic task of calculating the mean value over a single numeric attribute with *** on the previous schemes for mean estimation under LDP,we employ PLDP model to design novel schemes(LAP,DCP,PWP)to provide personalized privacy for each *** then theoretically analysis the worst-case variance of three proposed schemes and conduct experiments on synthetic and real datasets to evaluate the performance of three *** theoretical and experimental results show the optimality of PWP in the low privacy regime and a slight advantage of DCP in the high privacy regime.

关键词： personalized local differential privacy mean estimation crowdsensing model

来源：评论

学校读者我要写书评

暂无评论

SoVAR: Build Generalizable Scenarios from Accident Reports for Autonomous Driving Testing 24

SoVAR: Build Generalizable Scenarios from Accident Reports f...

引用

39th ACM/IEEE International Conference on Automated software Engineering, ASE 2024

作者： Guo, An Zhou, Yuan Tian, Haoxiang Fang, Chunrong Sun, Yunjian Sun, Weisong Gao, Xinyu Luu, Anh Tuan Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798400712487

Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenarios from real-world accident reports provide valuable resources for ADS testing, including critical scenarios and high-quality seeds. However, existing scenario reconstruction methods from accident reports often exhibit limited accuracy in information extraction. Moreover, due to the diversity and complexity of road environments, matching current accident information with the simulation map data for reconstruction poses significant *** this paper, we design and implement SoVAR, a tool for automatically generating road-generalizable scenarios from accident reports. SoVAR utilizes well-designed prompts with linguistic patterns to guide the large language model (LLM) in extracting accident information from textual data. Subsequently, it formulates and solves accident-related constraints in conjunction with the extracted accident information to generate accident trajectories. Finally, SoVAR reconstructs accident scenarios on various map structures and converts them into test scenarios to evaluate its capability to detect defects in industrial ADSs. We experiment with SoVAR, using the accident reports from the National Highway Traffic Safety Administration's (NHTSA) database to generate test scenarios for the industrial-grade ADS Apollo. The experimental findings demonstrate that SoVAR can effectively generate generalized accident scenarios across different road structures. Furthermore, the results confirm that SoVAR identified 5 distinct safety violation types that contributed to the crash of Baidu Apollo. © 2024 Copyright is held by the owner/author(s). Publication ri

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

Verifying Contextual Refinement with Ownership Transfer

引用

Journal of computer Science & technology 2021年第6期36卷 1342-1366页

作者： Zhao-Hui Li Xin-Yu Feng School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

Contextual refinement is a compositional approach to compositional verification of concurrent *** has been much work designing program logics to prove the contextual refinement between the object implementation and its abstract ***,these program logics for contextual refinement verification cannot support objects with resource ownership transfer,which is a common pattern in many concurrent objects,such as the memory management module in OS kernels,which transfers the allocated memory block between the object and *** this paper,we propose a new approach to give abstract and implementation independent specifications to concurrent objects with ownership *** also design a program logic to verify contextual refinement of concurrent objects *** abstract *** have successfully applied our logic to verifying an implementation of the memory management module,where the implementation is an appropriately simplified version of the original version from a real-world preemptive OS kernel.

关键词： contextual refinement program logic concurrent object ownership transfer verification

来源：评论

学校读者我要写书评

暂无评论

Modif-SegUnet: Innovatively Advancing Liver Cancer Diagnosis and Treatment through Efficient and Meaningful Segmentation of 3D Medical Images

Modif-SegUnet: Innovatively Advancing Liver Cancer Diagnosis...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Chenhang Jin, Yujian Liang, Jiayi Yang, YuHan Nie, Shanling Hai, Yang East China University of Science and Technology Department of Computer Science and Engineering Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China The University of Sydney Faculty of Engineering Sydney Australia

ISBN: (纸本)9798350337488

Hepatocellular Carcinoma (HCC) holds a record of high incidence and severe global harm. In tasks of liver cancer segmentation based on 3D medical images, the majority of methods have endeavored to enhance the 3D U-net by integrating the latest modules from the field of computer Vision (such as the transformer), often overlooking the distinct characteristics of liver components. We introduced a novel deep learning architecture, Modif-SegUnet, to circumvent this limitation. This architecture extends the U-net model by incorporating a 3D-modifiable attention module, thereby fostering a heightened focus on distinguishing between normal liver sections and lesions. Furthermore, Modif-SegUnet ingeniously amalgamates the 3D-modifiable attention module with the Modif-transformer block, enabling efficient capture of relevant and valuable full-text information in CT images that contain liver or tumor regions. We subjected the proposed Modif-SegUnet to evaluation on the Liver Tumor Segmentation benchmark dataset. Experimental outcomes indicate that our methodology surpasses state-of-the-art approaches in liver tumor segmentation, suggesting potential pathways for advancing the diagnosis and treatment of liver cancer. © 2023 IEEE.

关键词： 3D medical image attention CT Liver cancer Segmentation transformer U-Net

来源：评论

学校读者我要写书评

暂无评论

Hardware Computation Graph for DNN Accelerator Design Automation Without Inter-PU Templates

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Li, Jun Wang, Wei Li, Wu-Jun Nanjing University National Key Laboratory for Novel Software Technology School of Computer Science Jiangsu Nanjing210023 China

Existing deep neural network (DNN) accelerator design automation (ADA) methods adopt architecture templates to predetermine parts of design choices and then explore the remaining design choices beyond templates. Based on the architecture hierarchy at the processing unit (PU) level, these templates can be classified into intra-PU templates and inter-PU templates. Since templates limit the flexibility of ADA, designing effective ADA methods without templates has become an important research topic. Although there have appeared some works to enhance the flexibility of ADA by removing intra-PU templates, to the best of our knowledge no existing works have studied ADA methods without inter-PU templates. ADA with predetermined inter-PU templates is typically inefficient in terms of resource utilization, especially for DNNs with complex topology. In this paper, we propose a novel method, called hardware computation graph (HCG), for ADA without inter-PU templates. In HCG, a novel inter-PU architecture exploration strategy is proposed to optimize on-chip memory utilization. This strategy mainly depends on an appearing-frequency guided pruning method and an appearing-frequency first generation method. Experiments show that HCG can achieve competitive latency while using only 13% ⁓ 90% of on-chip memory, compared with existing state-of-the-art ADA methods. © 1982-2012 IEEE.

关键词： Integrated circuit design

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：