检索结果-内蒙古大学图书馆

Robotics and computer Vision (ICRCV), International Conference on

作者： Xiaowei Han Yunjing Lu Qiuyang Guo Jiwu Liu Chaolong Fei Postdoctoral research workstation of Northeast Asia Service Outsourcing Research Center Post-Doctoral Flow Station of Applied Economics Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin University of Commerce Harbi China Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin University of Commerce Harbin China Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Guangdong Technology College Zhaoqing China

ISBN: (数字)9798331527426

ISBN: (纸本)9798331527433

With the rapid development of information technology, video has become an important carrier for people to perceive information in daily life. If you want to analyze the action of people in the video data of various scenes and make use of the results, you must first identify the human action accurately. In this paper, a temporal self-attention module is proposed to help the network dynamically learn the correlation between different data frames, so as to better capture the dependency on the time of action. On this basis, a novel network structure, Channel-Temporal Self-Attention Block (C-TSAB), is further proposed. C-TSAB adaptively emphasizes the key channels of input features and focuses on the time dimension to enhance the model's ability to recognize and represent action features. In the ablation experiment, the Top-1 and Top-5 indicators in HMDB51 dataset were 58.54% and 81.70%, respectively, and the Top-1 and Top-5 indicators in UCF101 dataset were 58.54% and 82.73%, respectively. Comparative experiments were conducted on HMDB51 dataset and UCF101 dataset respectively, our model obtained a better Top-1 indicator, both of which were 58.54%, proving that our model has relatively good performance in video HAR task.

关键词： Solid modeling computer vision Three-dimensional displays Correlation Computational modeling Feature extraction Spatial databases Human activity recognition information technology Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

The Adaptive Fault-tolerant Routing Based on an Improved Local Security information Model of the Exchanged Hypercube 21

The Adaptive Fault-tolerant Routing Based on an Improved Loc...

引用

21st IEEE International Symposium on Parallel and Distributed processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Zhang, Yazhi Luo, Chuanwen Wang, Guijuan Zhang, Li Lv, Mengjie Yu, Jiguo Qilu University of Technology School of Computer Science and Technology Jinan China Beijing Forestry University School of Information Science and Technology Beijing China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Nanjing University of Posts and Telecommunications College of Computer Nanjing China Qilu University of Technology Shandong Academy of Sciences Big Data Research Institute Jinan China

ISBN: (纸本)9798350329223

With the increasing amount of computation in high-performance computing, the scale of interconnection networks is becoming larger and larger. It is inevitable that processors or links in the network become faulty. Therefore, it is very important for a processor to understand the security status of itself and neighbors, and then adaptively and reliably communicate. However, the existing security information models consider faulty processors or faulty links separately, and do not consider the situation where both processors and links fail simultaneously. The Exchanged Hypercube is an excellent interconnection network structure which achieves a balance between network functionality and hardware overhead while preserving many excellent properties of the Hypercube. In this paper, we propose an adaptive fault-tolerant routing algorithm of the Exchanged Hypercube based on an improved local security information model, which considers the faulty processors and faulty links simultaneously. This algorithm always can select suitable processors for routing based on the local security information and unsafe coefficients of processors, which greatly reduces the impact of the faulty of networks. The adaptive fault-tolerant routing algorithm of the Exchanged Hypercube network is not only suitable for regular networks but also for heterogeneous networks since the Exchanged Hypercube is a semi regular network. Sufficient experimental results show that the algorithm proposed in this paper has a lower packet loss rate, a higher success rate, and a shorter average path length. © 2023 IEEE.

关键词： Hypercube networks

来源：评论

学校读者我要写书评

暂无评论

Improved R3D for Human Action Recognition Based on Transfer Learning

Improved R3D for Human Action Recognition Based on Transfer ...

引用

Robotics and computer Vision (ICRCV), International Conference on

作者： Xiaowei Han Qiuyang Guo Yunjing Lu Jiwu Liu Chaolong Fei Postdoctoral research workstation of Northeast Asia Service Outsourcing Research Center Post-Doctoral Flow Station of Applied Economics Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin University of Commerce Harbi China Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin University of Commerce Harbin China Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Guangdong Technology College Zhaoqing China

ISBN: (数字)9798331527426

ISBN: (纸本)9798331527433

Human action recognition is an important research direction in the field of computer vision and machine learning, which is widely used in intelligent surveillance, human-computer interaction, sports analysis and other fields. Traditional action recognition methods usually rely on large-scale labeled datasets and complex feature extraction processes, which have problems such as high data acquisition cost and long model training time, as an effective solution, transfer learning can significantly improve the performance of the model and reduce the dependence on labeled data by transferring the features learned by the pre-trained model on large-scale datasets to the target task. In this paper, the R3D model is used as the backbone network, and the model is improved by strengthening the channel and temporal feature extraction capabilities. The model achieves good performance on Shopping Action_ v l by transfer learning based on HMDB51 and UCF101 datasets, and obtains 89.53% and 94.14% of the optimal Top-1 and Top-5 indicators after pre-training on UCF101 dataset. In summary, the C-TSAB ResNets model is proposed in this paper performs well in accuracy and robustness on human action recognition tasks through transfer learning, which verifies the actual effect of the innovation in the research work of this topic.

关键词： Training computer vision Technological innovation Target recognition Surveillance Transfer learning Neural networks Feature extraction Data models Human activity recognition

来源：评论

学校读者我要写书评

暂无评论

Ssd Optimization Model Based on Shallow Feature Fusion

SSRN

引用

SSRN 2022年

作者： Yang, Zhe Bu, Ziyu Liu, Chunping Provincial Key Laboratory for Computer Information Processing Technology Suzhou215006 China Department of Computer Science and Technology Soochow University Suzhou215006 China Provincial Key Laboratory for Intelligent Engineering in Big Data Suzhou215006 China

Object detection has been an important research branch in the field of computer vision. The single-shot-detection (SSD) is an object detection model based on deep learning, which can achieve a good balance between the detection accuracy and the detection speed, but has the problem of poor recognition accuracy for small objects. To address this limitation , this paper improves the structure of the SSD feature pyramid and upsamples the shallow feature map with small object information and fuses it with the upper feature map, thus enhancing the ability of the shallow feature map to represent detailed information. In this way, not only the overall detection accuracy of the SSD is improved, but also a relatively high detection speed is maintained. The proposed model is verified by experiments on two common datasets, the Pascal VOC and MS COCO datasets. On the PASCAL VOC07+12, MS COCO14, and VOC07+12 + COCO datasets, the improved model achieves the mean average precision values of 80.1% (+3.3% compared with the conventional model), 49.9% (+6.8%), and 82.1% (+3.0%), respectively. Meanwhile, the proposed model can achieve the detection speed of 42.2 frames per second. © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Optical scanning approach to image processing and holography

Optical scanning approach to image processing and holography

引用

Digital Optical Technologies 2023

作者： Poon, Ting-Chung Zhang, Yaping Yunnan Provincial Key Laboratory of Modern Information Optics Kunming University of Science and Technology Yunnan Kunming650500 China Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24061 United States

Optical scanning approach to image processing has advantages over frequency-plane architecture in terms of accuracy and flexibility. We will review an optical scanning approach to image processing that includes the ca... 详细信息

ISBN: (数字)9781510664586

ISBN: (纸本)9781510664579

关键词： Holography

来源：评论

学校读者我要写书评

暂无评论

SMWT: A Universal and Lightweight SDN-Based Meter Table Watermarking Traceback Scheme 24

SMWT: A Universal and Lightweight SDN-Based Meter Table Wate...

引用

24th Asia-Pacific Network Operations and Management Symposium, APNOMS 2023

作者： He, Heng Yang, Sen Zhou, Xiaohu Wang, Jia School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430081 China Guilin Medical University Guilin541001 China

ISBN: (纸本)9788995004395

The use of anonymous network has increased dramatically due to the development of network technology and people focus on the network security and privacy. However, anonymous networks are often used for illegal purposes, which has caused a significant increase in illegal transactions in the network. Therefore, it is necessary to investigate methods that can trace illegal transactions in anonymous networks. In this paper, we propose a universal and lightweight Software Defined Network (SDN)-based Meter table Watermarking Traceback scheme (SMWT), which is an active watermarking technology. SMWT uses the Bose-Chaudhuri-Hocquenghem (BCH) code as the encoding method and the flow rate as the carrier for the watermark to effectively trace flows of different communication protocols in various anonymous network environments. It utilises the SDN controller to install flow table entries and meter entries to the SDN switch, which can efficiently change the flow rate and embed the watermark in the flow in a stealthily manner. After the flow passes through the anonymous network, the SDN switch can extract the watermark using the flow rate and identify the two communicating parties. We have conducted experiments to evaluate SMWT in a real anonymous network Tor. Compared with other relevant existing schemes, SMWT demonstrated a higher detection rate of 96.7% and a lower false positive rate of 0.3%, as well as high flexibility and stealthiness, low deployment difficulty and controller load. Copyright 2023 KICS.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Multi-photon neuron embedded bionic skin for high-precision complex texture and object reconstruction perception research

引用

Opto-Electronic Advances 2025年第2期8卷 29-44页

作者： Hongyu Zhou Chao Zhang Hengchang Nong Junjie Weng Dongying Wang Yang Yu Jianfa Zhang Chaofan Zhang Jinran Yu Zhaojian Zhang Huan Chen Zhenrong Zhang Junbo Yang College of Science National University of Defense TechnologyChangsha 410073China Key Laboratory of Multimedia Communication and Network Technology in Guangxi School of ComputerElectronics and InformationGuangxi UniversityNanning 530004China College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China College of Meteorology and Oceanography National University of Defense TechnologyChangsha 410073China Hunan Provincial Key Laboratory of Novel Nano-Optoelectronic Information Materials and DevicesNational University of Defense TechnologyChangsha 410073China College of Advanced Interdisciplinary Studies National University of Defense TechnologyChangsha 410073China

Attributable to the complex distribution of tactile vesicles under the skin and the ability of the brain to process specific tactile parameters(shape,hardness,and surface texture),human skin can have the capacity for tactile spatial reconstruction and visualization of complex object geometry and surface ***,current haptic sensor technologies are predominantly point sensors,which do not have an interlaced distribution structure similar to that of haptic vesicles,limiting their potential in human-computer interaction ***,we report an optical microfiber array skin(OMAS)imitating tactile vesicle interlaced structures for tactile visualization and object reconstruction *** device is characterized by high sensitivity(−0.83 N/V)and fast response time(38 ms).We demonstrate that combining the signals collected by the OMAS with appropriate artificial intelligence algorithms enables the recognition of objects with different hardnesses and shapes with 100%*** also allows for the classification of fabrics with different surface textures with 98.5%accuracy and Braille patterns with 99%*** a proof-of-concept,we integrated OMAS into a robot arm to select mahjong among six common objects and successfully recognize its suits by touch,which provides a new solution for tactile sensory processing for human-computer interaction.

关键词： multiphoton neurons human-computer interaction tactile sensing tactile imaging tactile spatial reconstruction

来源：评论

学校读者我要写书评

暂无评论

Ssd Optimization Model Based on Shallow Feature Fusion

SSRN

引用

SSRN 2022年

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training 24

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Lang...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availability of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly available image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are available at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Joint Sparsification and Quantization for Wireless Federated Learning under Communication Constraints 24

Joint Sparsification and Quantization for Wireless Federated...

引用

24th IEEE International Workshop on Signal processing Advances in Wireless Communications, SPAWC 2023

作者： Su, Junshen Wang, Xijun Chen, Xiang Cheng, Ray-Guang Sun Yat-Sen University School of Electronics and Information Technology Guangzhou China The Chinese University of HongKong Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen China National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei Taiwan

ISBN: (纸本)9781665496261

Communication efficiency is one of the key bottlenecks in Federated Learning (FL). Compression techniques, such as sparsification and quantization, are used to reduce communication overhead. However, joint designs of these techniques under communication constraints are not well-explored. This paper investigates the joint uplink compression problem in communication-constrained FL systems. We propose a Block-TopK sparsification scheme to reduce the proportion of bits used for locating entries of a sparsified vector. Considering the communication constraints, an optimization formulation is proposed to minimize the compression error. By solving the optimization problem, our joint compression method provides a better trade-off between sparsity budget and bit width. Numerical results demonstrate that our approach achieves 99.96% of baseline accuracy with only 1.56% of the baseline communication overhead when training ResNet-18 on CIFAR-10. © 2023 IEEE.

关键词： Budget control

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：