检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Yongkang Li, Jun Wu, Guoming Zhang, Han Shi, Zhiping Liu, Zhaoxun Wu, Zizhang Jiang, Na The Information Engineering College Capital Normal University Beijing100048 China The State Key Lab of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China The Computer Vision Perception Department of ZongMu Technology Shanghai201203 China

In recent years, 2D Convolutional Networks-based video action recognition has encouragingly gained wide popularity;However, constrained by the lack of long-range non-linear temporal relation modeling and reverse motion information modeling, the performance of existing models is, therefore, undercut seriously. To address this urgent problem, we introduce a startling Temporal Transformer Network with Self-supervision (TTSN). Our high-performance TTSN mainly consists of a temporal transformer module and a temporal sequence self-supervision module. Concisely speaking, we utilize the efficient temporal transformer module to model the nonlinear temporal dependencies among non-local frames, which significantly enhances complex motion feature representations. The temporal sequence self-supervision module we employ unprecedentedly adopts the streamlined strategy of "random batch random channel" to reverse the sequence of video frames, allowing robust extractions of motion information representation from inversed temporal dimensions and improving the generalization capability of the model. Extensive experiments on three widely used datasets (HMDB51, UCF101, and Something-something V1) have conclusively demonstrated that our proposed TTSN is promising as it successfully achieves state-of-the-art performance for action recognition. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Improved Multi-Head Self-Attention Classification Network for Multi-View Fetal Echocardiography Recognition

Improved Multi-Head Self-Attention Classification Network fo...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yingying Zhang Haogang Zhu Yan Wang Jingyi Wang Yihua He School of Biological Science and Medical Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Instrumentation and Optoelectronic Engineering Beihang University Beijing China Echocardiography Medical Center Beijing Anzhen Hospital Capital Medical University Beijing China Maternal-Fetal Medicine Center in Fetal Heart Disease Beijing Anzhen Hospital Beijing China

The accurate acquisition of multiview fetal cardiac ultrasound images is very important for the diagnosis of fetal congenital heart disease (FCHD). However, these manual clinical procedures have drawbacks, e.g., varying technical capabilities and inefficiency. Therefore, exploring automatic recognition method for multiview images of fetal heart ultrasound scans is highly desirable to improve prenatal diagnosis efficiency and accuracy. In this work, we propose an improved multi-head self-attention mechanism called IMSA combined with residual networks to stably solve the problem of multiview identification and anatomical structure localization. In details, IMSA can capture short- and long-range dependencies from different subspaces and merge them to extract more precise features, thus making use of the correlation between fetal heart structures to make view recognition more focused on anatomical structures rather than disturbing regions, such as artifacts and speckle noises. We validate our proposed method on fetal cardiac ultrasound imaging datasets from a single center and 38 multicenter studies and the results outperform other state-of-the-art networks by 3%-15% of F1 scores in fetal heart six standard view *** Relevance— This technology has great potential in assisting cardiologists to complete the automatic acquisition of multi-section fetal echocardiography images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boundary guided context aggregation for semantic segmentation

arXiv

引用

arXiv 2021年

作者： Ma, Haoxiang Yang, Hongyu Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China Beihang University School of Computer Science and Engineering Beijing China Beihang University Institute of Artificial Intelligence Beijing China

The recent studies on semantic segmentation are starting to notice the significance of the boundary information, where most approaches see boundaries as the supplement of semantic details. However, simply combing boundaries and the mainstream features cannot ensure a holistic improvement of semantics modeling. In contrast to the previous studies, we exploit boundary as a significant guidance for context aggregation to promote the overall semantic understanding of an image. To this end, we propose a Boundary guided Context Aggregation Network (BCANet), where a Multi-Scale Boundary extractor (MSB) borrowing the backbone features at multiple scales is specifically designed for accurate boundary detection. Based on which, a Boundary guided Context Aggregation module (BCA) improved from Non-local network is further proposed to capture long-range dependencies between the pixels in the boundary regions and the ones inside the objects. By aggregating the context information along the boundaries, the inner pixels of the same category achieve mutual gains and therefore the intra-class consistency is enhanced. We conduct extensive experiments on the Cityscapes and ADE20K databases, and comparable results are achieved with the state-of-the-art methods, clearly demonstrating the effectiveness of the proposed one. Our code is availab.e at https://***/mahaoxiang822/Boundary-Guided-Context-Aggregation. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective

arXiv

引用

arXiv 2022年

作者： Zhang, Jiawei Wang, Xiang Bai, Xiao Wang, Chen Huang, Lei Chen, Yimin Gu, Lin Zhou, Jun Harada, Tatsuya Hancock, Edwin R. School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China SKLSDE Institute of Artificial Intelligence Beihang University Beijing China RIKEN AIP Tokyo Japan The University of Tokyo Japan Griffith University Australia University of York United Kingdom

Despite recent stereo matching networks achieving impressive performance given sufficient training data, they suffer from domain shifts and generalize poorly to unseen domains. We argue that maintaining feature consistency between matching pixels is a vital factor for promoting the generalization capability of stereo matching networks, which has not been adequately considered. Here we address this issue by proposing a simple pixel-wise contrastive learning across the viewpoints. The stereo contrastive feature loss function explicitly constrains the consistency between learned features of matching pixel pairs which are observations of the same 3D points. A stereo selective whitening loss is further introduced to better preserve the stereo feature consistency across domains, which decorrelates stereo features from stereo viewpoint-specific style information. Counter-intuitively, the generalization of feature consistency between two viewpoints in the same scene translates to the generalization of stereo matching performance to unseen domains. Our method is generic in nature as it can be easily embedded into existing stereo networks and does not require access to the samples in the target domain. When trained on synthetic data and generalized to four real-world testing sets, our method achieves superior performance over several state-of-the-art networks. The code is availab.e online. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Distant supervised relation extraction with separate head-tail cnn 5

Distant supervised relation extraction with separate head-ta...

引用

5th Workshop on Noisy User-Generated Text, W-NUT@EMNLP 2019

作者： Xing, Rui Luo, Jie State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University China

ISBN: (纸本)9781950737840

Distant supervised relation extraction is an efficient and effective strategy to find relations between entities in texts. However, it inevitably suffers from mislab.ling problem and the noisy data will hinder the performance. In this paper, we propose the Separate Head- Tail Convolution Neural Network (SHTCNN), a novel neural relation extraction framework to alleviate this issue. In this method, we apply separate convolution and pooling to the head and tail entity respectively for extracting better semantic features of sentences, and coarseto- fine strategy to filter out instances which do not have actual relations in order to alleviate noisy data issues. Experiments on a widely used dataset show that our model achieves significant and consistent improvements in relation extraction compared to statistical and vanilla CNN-based methods. © 2019 Association for Computational Linguistics

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An energy prediction model for cloud data centers through performance counter

引用

International Journal of Performability engineering 2019年第11期15卷 2962-2971页

作者： Meng, Sa Sun, Peng Luo, Jie Xu, Han School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China

In recent years, with an increased environmental protection concern, the carbon footprints of large-scale cloud data centers have come into public view. Energy efficiency has become a key indicator for these data centers. Management personnel in cloud data centers should know the relationship between the workload patterns and the energy consumption of the infrastructure in order to optimize energy efficiency. In this paper, we first discuss the energy consumption problems of cloud data centers and summarize the related work. Then, we purpose an energy prediction model to estimate the energy consumption of servers in cloud data centers based on performance counters of their processors. Afterward, the proposed model is tested and analyzed under a wide selection of benchmarks, including SPEC2006, I/Ozone, and Netperf. Finally, through analyzing the results of the contrast experiments, it is shown that the proposed energy prediction model can predict energy consumption of cloud servers with high accuracy. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

state synchronization in process-oriented chaincode

引用

Frontiers of computer science 2019年第6期13卷 1166-1181页

作者： Lian YU Wei-Tek TSAI School of Software&Microelectronics Peking UniversityBeijing 102600China State Key Laboratory of Software Development Environment School of Computer Science&EngineeringBeihang UniversityBeijing 100191China Comp. Info.and Dec.Systems EngineeringArizona State UniversityTempeAZ 85287USA

Business processes often involve operational processes,contracts,and *** modeling of such processes must address regulation monitoring and enforcement and maintain a reliable history of data for *** study proposes modeling business processes as chaincode(CC)on permissioned blockchains(BCs).The challenges encountered by the proposed approach are state synchronizations among distributed nodes(called authnodes)and realtime *** study separates CC executions from the state management of multiple BCs and demonstrates the validity of the proposed approach with a payment authorization system at a Chinese bank.

关键词： blockchains state synchronization chaincode permissioned blockchains concurrent block building

来源：评论

学校读者我要写书评

暂无评论

Efficient Token Compression for Vision Transformer with Spatial Information Preserved

arXiv

引用

arXiv 2025年

作者： Mao, Junzhu Shen, Yang Guo, Jinyang Yao, Yazhou Hua, Xiansheng School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory of Software Development Environment Institute of Artificial Intelligence Beihang University Beijing100191 China Terminus Group Beijing100027 China

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token compression method called Prune and Merge. Our approach integrates token pruning and merging operations within transformer models to achieve layer-wise token compression. By introducing trainable merge and reconstruct matrices and utilizing shortcut connections, we efficiently merge tokens while preserving important information and enabling the restoration of pruned tokens. Additionally, we introduce a novel gradient-weighted attention scoring mechanism that computes token importance scores during the training phase, eliminating the need for separate computations during inference and enhancing compression efficiency. We also leverage gradient information to capture the global impact of tokens and automatically identify optimal compression structures. Extensive experiments on the ImageNet-1k and ADE20K datasets validate the effectiveness of our approach, achieving significant speed-ups with minimal accuracy degradation compared to state-of-the-art methods. For instance, on DeiT-Small, we achieve a 1.64× speed-up with only a 0.2% drop in accuracy on ImageNet-1k. Moreover, by compressing segmenter models and comparing with existing methods, we demonstrate the superior performance of our approach in terms of efficiency and effectiveness. Code and models have been made availab.e at https://***/ NUST-Machine-Intelligence-lab.ratory/prune_and_merge. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Design and Validation of a Hyper-converged Blockchain Hardware and software System Based on Domestic Chips 1st

Design and Validation of a Hyper-converged Blockchain Hardwa...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Liu, Xiaolong Yuan, Bo Wu, Faguo Enterprise Technology Center Aerospace Legione Technology Co. Ltd Haidian Beijing100195 China School of Computer Science and Engineering Beihang University Haidian Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Haidian Beijing100191 China Institute of Artificial Intelligence Beihang University Haidian Beijing100191 China Beihang University Haidian Beijing100191 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Haidian Beijing100191 China

ISBN: (纸本)9789819794119

This paper proposes a hyper-converged blockchain hardware and software sys-tem based on domestic chips. By utilizing domestically firmware, the Linux operating system, X86 architecture Hygon processors, and ARM architecture Phytium processors, combined with servers, storage, network, and independently controllab.e blockchain technologies, the system achieves integrated hardware and software optimization. This significantly improves performance and scalab.lity. Experimental results demonstrate that the system performs excellently in various high-security application scenarios, providing reliable solutions for government, finance, taxation, transportation, energy, and telecommunications sectors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

SARLR: Self-adaptive recommendation of learning resources 14

SARLR: Self-adaptive recommendation of learning resources

引用

14th International Conference on Intelligent Tutoring Systems Workshops, ITS 2018

作者： Liu, Liping Wu, Wenjun Huang, Jiankun State Key Lab of Software Development Environment Department of Computer Science and Engineering Beihang University Beijing China

Personalized recommendation is important for online students to select rich learning resources and make their own learning schedules. We propose SARLR, a new self-adaptive recommendation algorithm of online learning resources. The SARLR algorithm integrates an IRT-based learning cognitive model named T-BMIRT into the recommendation framework and is able to adaptively adjust learning path recommendations based on dynamic of individual learning process. The experimental results show that the SARLR algorithm outperforms the existing recommendation algorithms. © 2019 CEUR-WS. All rights reserved.

关键词： Learning algorithms

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：