检索结果-内蒙古大学图书馆

IEEE/CVF conference on computer Vision and Pattern Recognition (CVPR)

作者： Tang, Huayi Liu, Yong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Multi-view clustering has been shown to boost clustering performance by effectively mining the complementary information from multiple views. However, we observe that learning from data with more views is not guaranteed to achieve better clustering performance than from data with fewer views. To address this issue, we propose a general deep learning based framework that is guaranteed to reduce the risk of performance degradation caused by view increase. Concretely, the model is trained to simultaneously extract complementary information and discard the meaningless noise by automatically selecting features. These two learning procedures are incorporated into one unified framework by the proposed optimization objective. In theory, the empirical clustering risk of the model is no higher than learning from data before the view increase and data of the new increased single view. Also, the expected clustering risk of the model under divergence-based loss is no higher than that with high probability. Comprehensive experiments on benchmark datasets demonstrate the effectiveness and superiority of the proposed framework in achieving safe multi-view clustering.

关键词： Degradation Deep learning computer vision Computational modeling Feature extraction Robustness Data models

来源：评论

学校读者我要写书评

暂无评论

Application of computer information technology in college physical education using fuzzy evaluation theory

引用

COMPUTATIONAL INTELLIGENCE 2021年第3期37卷 1181-1198页

作者： Yu, Shan-an Shanghai Univ Elect Power Dept Phys Educ Shanghai 200090 Peoples R China

The educational sector faces a new dimension that is dominated by lifelong learning and is affected by the technical, social, and cultural changes. This pattern represents the need to improve the teaching methods for physical education and sports science. The use of computers and other information technology to increase the effectiveness of the teaching process is a modern method. This paper aims to illustrate the use of information and communication technologies (ICT) in physical education and sports. In our field, the gradual computerization results can be summed up in the following aspects: education software, design, and planning activities, recording outcomes, motion monitoring, video analysis, comparison of performance and synchronizing, measurements at distance and time and the evaluation of the activity. Although physical education and sports are practical activities, specialists can make use of modern teaching technologies. In this paper, the system of curriculum assessment for physical education has been analyzed and researched in computer assessment. The first section introduced the method of assessment of the physical education program. The second phase of the paper represents a teaching model of the physical education mathematical model utilizing the Comprehensive Adaptive Fuzzy Evaluation Theory has been proposed. A new level is the modernization of physics education with the artificial intelligence computer education system built in this paper. The experimental results have high performance in detecting the physical activity of college students.

关键词： computer information technology fuzzy evaluation theory ICT physical education

来源：评论

学校读者我要写书评

暂无评论

VIDEO-ANALYTICS TASK-AWARE QUAD-TREE PARTITIONING AND QUANTIZATION FOR HEVC 29

VIDEO-ANALYTICS TASK-AWARE QUAD-TREE PARTITIONING AND QUANTI...

引用

IEEE International conference on Image Processing (ICIP)

作者： Singh, Praneet Delp, Edward J. Reibman, Amy R. Purdue Univ Elmore Sch Elect & Comp Engn W Lafayette IN USA

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Video analytics systems designed for computer vision tasks use deep learning models that rely on high-quality input data to maximize performance. However, in a real-world system, these inputs are often compressed using video codecs such as HEVC. Video compression degrades the quality of the inputs, thereby degrading the performance of these models. Region-of-interest (ROI) coding enables bits to be allocated to improve performance;however, the method to select regions should be computationally simple since it must occur during or before the video is compressed and transmitted for further processing. In this paper, we propose a task-aware quad-tree (TA-QT) partitioning and quantization method to achieve ROI coding for HEVC and other video coding standards. TAQT uses a lightweight edge-based model to guide task-aware video encoding to improve end-stage video analytics (ESVA) performance while reducing both bit-rate and encoding time. We demonstrate the effectiveness of our approach in terms of (a) the performance of the ESVA on compressed inputs, (b) transmission bit-rates, and (c) encoding time.

关键词： Video analytics computer vision deep learning HEVC HM video compression task-aware

来源：评论

学校读者我要写书评

暂无评论

Utilizing Organizational Patterns to Build high-Performing Remote Teams 28

Utilizing Organizational Patterns to Build High-Performing R...

引用

28th European conference on Pattern Languages of programs, EuroPLoP 2023

作者： Toldy, Kristián Khail, Waheedullah Sulaiman Vranic, Valentino Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology Bratislava Slovakia Helmholtz-Zentrum Berlin für Materialien Energie Gmbh Germany

ISBN: (纸本)9798400700408

In recent years, remote work has become a more popular option for companies across various industries. While remote work provides numerous benefits, such as flexibility and increased work-life balance, it also presents unique challenges that can hinder team collaboration, productivity, and overall success. In order to overcome these obstacles, it is essential to adopt effective organizational patterns that can help build high-performing remote teams. Building a high-performing remote team requires a set of strategies with some key focus points to be kept in mind such as communication, trust, goals, collaboration, and performance. For all of these, there have been an extensive research and publication of observed patterns to which we have also contributed with a new set of these four patterns: Use Common Language, Discuss Publicly, Lights, Camera, Action!, and Praise in Public, Correct in Private. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： computer programming

来源：评论

学校读者我要写书评

暂无评论

Altering 5G Network Parameters Using Deep Reinforcement Learning to Optimize QoS and Security 2

Altering 5G Network Parameters Using Deep Reinforcement Lear...

引用

2nd IEEE Virtual conference on Communications, VCC 2024

作者： Kaddour, Hamza Olaveson, Israel G. Krome, Cameron J. Fouda, Mostafa M. Idaho State University Department of Electrical and Computer Engineering PocatelloID83209 United States Idaho FallsID83401 United States Ai Data and Visualization Ai Data and Visualization Idaho FallsID83415 United States

ISBN: (纸本)9798331530099

As 5G networks rapidly expand to support higher data rates, lower latency, and increased device density, the associated security risks are also growing. That is why the deployment of 5G networks introduces significant challenges in balancing Quality of Service (QoS) and security, especially in dynamic, high-demand environments. This paper presents a framework leveraging deep reinforcement learning (DRL) to optimize this tradeoff based on our generated QoS_5G_Sec dataset. We evaluated various DRL agents, including Deep Q-Network (DQN), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), focusing on their ability to manage network parameters in real-time. Among the tested methods, the DQN model tuned using the Optuna hyperparameter optimization technique demonstrated the best overall performance. Our results show that this approach provides a robust solution for dynamically adjusting network parameters, improving both QoS and security in 5G network architectures. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

computer modeling of stray light for high-resolution spectrometer 8

Computer modeling of stray light for high-resolution spectro...

引用

8th International conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Zhang, Qian Wang, Hongmin Wang, Weigang Li, Sheng An, Ning Hu, Bin Liu, Lu Zhang, Dong Beijing Institute of Space Mechanics and Electricity Beijing China

ISBN: (纸本)9798350302455

Stray light is an important indicator that affects the performance of a high-resolution spectrometer system. In order to improve the spectral resolution of the spectrometer system, this paper proposes a computer modeling method of stray light based on the surface attribute modeling of system components and a complete system stray light analysis. This method takes full account of the effects of specular roughness, surface scratches, and surface particle contamination on the stray light of the system. Base on available optical elements and simplified mechanical structure, the roughness scattering model, surface particle pollution scattering model, and surface scratch scattering model can be constructed respectively according to different parameters. The influence and proportion of stray light caused by different surface attributes can be quantitatively calculated and analyzed. The analysis results show that the proposed method can obtain the mechanism path composition of stray light more accurately, and provide more effective support for the design of stray light suppression. © 2023 IEEE.

关键词： Spectrometers

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition Based on BERT-BiLSTM-SPAN in Low Resource Scenarios 15

Named Entity Recognition Based on BERT-BiLSTM-SPAN in Low Re...

引用

15th International conference on computer Research and Development, ICCRD 2023

作者： Weng, Maobin Zhang, Weiwen School of Computer Science and Technology Guangdong University of Technology Guangzhou China

ISBN: (纸本)9781665487504

The task of named entity recognition (NER) is crucial in the creation of knowledge graphs. With the advancement of deep learning, the pre-training model BERT has become the mainstream solution for NER. However, lack of corpus leads to poor performance of NER models using BERT alone. In low resource scenarios, previous work has focused on merging complex information to model or transfer learning from high resource corpora. Therefore, a simple but effective strategy for fully utilizing the corpus is required. In this paper, we focus on recognizing entities under resource constraints. We propose BERT-BiLSTM-SPAN for low resource scenarios, where BERT is used as an embedding layer, combined with BiLSTM and a decoding layer using a span pointer decoding algorithm. To make our model more robust, we employ adversarial training and data augmentation techniques. We conduct experiments on the marine news dataset. The BERT-BiLSTM-SPAN achieves an 80.11% F1-score. Furthermore, experimental results of data augmentation and adversarial training are both encouraging. Therefore, our proposed solutions show suitability in low resource scenarios. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards high-throughput and Low-latency Billion-scale Vector Search via CPU/GPU Collaborative Filtering and Re-ranking 23

Towards High-throughput and Low-latency Billion-scale Vector...

引用

23rd USENIX conference on File and Storage Technologies, FAST 2025

作者： Tian, Bing Liu, Haikun Tang, Yuhang Xiao, Shihai Duan, Zhuohui Liao, Xiaofei Jin, Hai Zhang, Xuecang Zhu, Junhua Zhang, Yu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd. China

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN;2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy. © 2025 FAST. 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

high-Accuracy and Energy-Efficient Action Recognition with Deep Spiking Neural Network 29th

High-Accuracy and Energy-Efficient Action Recognition with D...

引用

29th International conference on Neural Information Processing

作者： Zhang, Jingren Wang, Jingjing Di, Xie Pu, Shiliang Hangzhou Hikvis Digital Technol Co Ltd Hikvis Res Inst Hangzhou Peoples R China

ISBN: (纸本)9783031301070;9783031301087

In recent years, spiking neural networks (SNNs) received significant attention as the third generation of networks and have successfully been employed in energy-efficient image classification tasks. However, typical SNN construction methods still suffer from problems such as high inference latency or incompatibility with complicated models. Thus, applications of SNNs are limited to relatively simple tasks. In this paper, we establish an SNN-based action recognition model which aims at a more challenging video classification task. Specifically, the action recognition SNN model with a deep two-stream architecture is constructed with a hybrid conversion method combining channel-wise normalization and tandem learning. A skipping-step rate decoder is applied to decrease the conversion errors and improve the transmission accuracy. A new conversion and inference method for recurrent spiking neural network (RSNN) is introduced into the framework. The tandem learning method with bounded ReLU (bReLU) function is employed to fine-tune the normalized SNN parameters, decreasing the inference latency while still preserving high accuracy. Experiments on UCF-101 show that our proposed model obtains an accuracy of 88.46% with only 200 time steps, which achieves a high-accuracy and energy-efficient performance in SNN.

关键词： spiking neural network action recognition ANN-to-SNN conversion tandem learning

来源：评论

学校读者我要写书评

暂无评论

Parameter-Efficient Instance-Adaptive Neural Video Compression 17th

Parameter-Efficient Instance-Adaptive Neural Video Compressi...

引用

17th Asian conference on computer Vision, ACCV 2024

作者： Oh, Seungjun Yang, Hyunmo Park, Eunbyung Department of Artificial Intelligence Sungkyunkwan University Suwon Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9789819609079

Learning-based Neural Video Codecs (NVCs) have emerged as a compelling alternative to standard video codecs, demonstrating promising performance, and simple and easily maintainable pipelines. However, NVCs often fall short of compression performance and occasionally exhibit poor generalization capability due to inference-only compression scheme and their dependence on training data. The instance-adaptive video compression techniques have recently been suggested as a viable solution, fine-tuning the encoder or decoder networks for a particular test instance video. However, fine-tuning all the model parameters incurs high computational costs, increases the bitrates, and often leads to unstable training. In this work, we propose a parameter-efficient instance-adaptive video compression framework. Inspired by the remarkable success of parameter-efficient fine-tuning on large-scale neural network models, we propose to use a lightweight adapter module that can be easily attached to the pretrained NVCs and fine-tuned for test video sequences. The resulting algorithm significantly improves compression performance and reduces the encoding time compared to the existing instant-adaptive video compression algorithms. Furthermore, the suggested fine-tuning method enhances the robustness of the training process, allowing for the proposed method to be widely used in many practical settings. We conducted extensive experiments on various standard benchmark datasets, including UVG, MCL-JVC, and HEVC sequences, and the experimental results have shown a significant improvement in rate-distortion (RD) curves (up to 5 dB PSNR) and BD rates compared to the baselines NVC. Our code is available on https://***/ohsngjun/PEVC. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image compression

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：