检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Haozhe Liu Haoqian Wu Weicheng Xie Feng Liu Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative regions, but ignores the auxiliary features when learning, leading to the lack of feature diversity for final judgment. In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. The feature maps with different activation distribution are then processed separately to take the feature independence into account. CNN is finally guided to learn richer discriminative features hierarchically for robust classification according to the proposed regularization. Our method is comprehensively evaluated under multiple settings, including classification against corruptions, adversarial attacks and low data regime. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both robustness and generalization performances, when compared with the state-of-the-art methods. Code is available at https://***/LinusWu/TENET_Training.

关键词： Training Computer vision Codes Heuristic algorithms Robustness Classification algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An SGX and Blockchain-Based system for Federated Learning in Classifying COVID-19 Images

An SGX and Blockchain-Based System for Federated Learning in...

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Sihang Qin Xianjun Gu Xing Jun Haitao Li Mengqi Huang Weiqi Dai Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China State Grid Wuhan Power Supply Company China

Federated learning, an emerging distributed learning framework, has gained prominence recently. However, two challenges arise when applying federated learning to medical data. The first challenge stems from the inability of model-generating nodes to ensure computational fairness. The second challenge involves the potential leakage of private information through gradient differences. This paper introduces a federated learning system that leverages Software Guard Extensions (SGX) and blockchain technology to enhance the fairness and security of federated learning for analyzing chest imaging data. The modeling of imaging factors for chest radiography data can effectively regulate the data quality of semi-trusted nodes. A blockchain smart contract is employed for data quality-aware proof, and the quality-aware block undergoes a two-stage rewriting process across distinct nodes. A notary membership model achieves notarized cluster consensus for imaging informatics data. The multi-channel layer model quantifies the distribution of computational workload across participating nodes within the medical consortium. Upon successful verification of the enclave command in the aggregation cycle, traceable and packaged signatures are generated to support computational fairness. To ensure robust information security, SGX remote authentication is used between downstream and upstream nodes. The federated learning system, built upon SGX and blockchain, has been implemented using the Fabric federated chain platform. The ResNet model underwent training through cross-sectional federated learning to effectively classify novel coronavirus lung medical image data. Following this, multiple experimental control and security analyses were conducted, revealing that the time loss incurred due to crossing channels is approximately 21.31%, while the time overhead of SGX remains within 5.2%, as allowed by the number of nodes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Authoring tool of sharable question items based on QTI specification for e-learning assessment

Authoring tool of sharable question items based on QTI speci...

引用

2017 Asia-Pacific Computational Intelligence and Information technology Conference

作者： Tien-Wen Sung You-Te Lu Chia-Jung Lee Yuan-Hsun Liao Chyun-Chyi Chen Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Information Science and EngineeringFujian University of Technology Department of Information and Communication Southern Taiwan University of Science and Technology Department of Information Management Tainan University of Technology Department of Management Information System Far East University

Although online examination for e-learning is widely realized *** the production of question bank is *** paper proposes an assessment authoring tool to assist teachers in creating reusable test question *** items conforms to the IMS Question and Test Interoperability(QTI) specification and are easy to share,reuse,exchange,and access across distributed learning management systems(LMS).system design and implementation were presented in this paper for sharing and contributing development experiences to related works.

关键词： system IMS Authoring tool of sharable question items based on QTI specification for e-learning assessment

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dynamic Multimodal Optimzation

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dy...

引用

Congress on Evolutionary Computation

作者： Xunfeng Wu Songbai Liu Junkai Ji Lijia Ma Victor C. M. Leung College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases.

关键词： Training Heuristic algorithms Computational modeling Sociology Clustering algorithms Evolutionary computation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

An Omnidirectional Antenna with Wide Bandwidth and High Gain for WiFi-5 and WiFi-6 Applications

An Omnidirectional Antenna with Wide Bandwidth and High Gain...

引用

IEEE International Conference on Electronic Information and Communication technology (ICEICT)

作者： Baifa Yang Haixuan Huang Botao Feng Li Deng College of Electronics and Information Engineering Shenzhen University Shenzhen China College of Big Data and Internet Shenzhen Technology University Shenzhen China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9781728190457

ISBN: (纸本)9781728190464

This paper proposes an omni-directional printed antenna with broadband and high gain for WiFi-5 and WiFi-6 applications. In order to achieve stable omnidirectional gain, both of the ground plane and the radiating elements are arranged on the same side of the printed circuit board (PCB) substrate. Over the whole working frequency band, selecting the left end of the PCB board to supply power helps to achieve good radiation pattern in the H-plane. Simulated results exhibit that a relative bandwidth of 8% (5.15-7.125 GHz) is obtained. The corresponding gain ranges from 5.14 to 7.74 dBi in the operating band, which is about 4 dBi larger than that of the conventional omnidirectional antennas.

关键词： Conferences Printed circuits Omnidirectional antennas Bandwidth Information and communication technology Broadband antennas Substrates

来源：评论

学校读者我要写书评

暂无评论

An Omni-directional Antenna with High Gain for WiFi-6 Applications

An Omni-directional Antenna with High Gain for WiFi-6 Applic...

引用

IEEE International Conference on Electronic Information and Communication technology (ICEICT)

ISBN: (数字)9781728190457

ISBN: (纸本)9781728190464

This paper presents a compact high-gain omnidirectional antenna for WiFi-6 applications. The antenna is basically comprised of three pairs of printed dipole patches in series, a coplanar waveguide (CPW) feeding structure and a choking coil, respectively. The printed dipoles fed in series are used to increase radiation gain while the choking coil is employed to provide stable radiation pattern as well as good impedance matching. The simulated results show that a frequency bandwidth of 9.8% (5-7.45 GHz) (S 11

关键词： Dipole antennas Impedance matching Conferences Omnidirectional antennas Coplanar waveguides Information and communication technology Gain

来源：评论

学校读者我要写书评

暂无评论

When to update your model: constrained model-based reinforcement learning 22

When to update your model: constrained model-based reinforce...

引用

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Tianying Ji Yu Luo Fuchun Sun Mingxuan Jing Fengxiang He Wenbing Huang Department of Computer Science and Technology Tsinghua University Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences JD Explore Academy *** Inc Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9781713871088

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos

arXiv

引用

arXiv 2023年

作者： Fang, Xiang Liu, Daizong Zhou, Pan Nan, Guoshun Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China Peking University China Beijing University of Posts and Telecommunications China

Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual features extracted from the consecutive decoded frames and fail to handle the compressed videos for query modelling, suffering from insufficient representation capability and significant computational complexity during training and testing. In this paper, we pose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input. To handle the raw video bit-stream input, we propose a novel Three-branch Compressed-domain Spatial-temporal Fusion (TCSF) framework, which extracts and aggregates three kinds of low-level visual features (I-frame, motion vector and residual features) for effective and efficient grounding. Particularly, instead of encoding the whole decoded frames like previous works, we capture the appearance representation by only learning the I-frame feature to reduce delay or latency. Besides, we explore the motion information not only by learning the motion vector feature, but also by exploring the relations of neighboring frames via the residual feature. In this way, a three-branch spatial-temporal attention layer with an adaptive motion-appearance fusion module is further designed to extract and aggregate both appearance and motion information for the final grounding. Experiments on three challenging datasets shows that our TCSF achieves better performance than other state-of-the-art methods with lower complexity. Copyright © 2023, The Authors. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition

Multi-Scale Dynamic and Hierarchical Relationship Modeling f...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zihan Wang Siyang Song Cheng Luo Songhe Deng Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Universiry of Leicester Monash University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hi-erarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatiotemporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and mag-nitude in different AUs' activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://***/CVI-SZU/MDHR.

关键词： Gold Adaptation models Computer vision Graphical models Codes Adaptive systems Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detection

arXiv

引用

arXiv 2023年

作者： Wang, Zihan Song, Siyang Luo, Cheng Zhou, Yuzhi Wu, Shiling Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computing and Mathematical Sciences University of Leicester United Kingdom

This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence;(ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation;and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition. Our code is publicly available at https://***/wzh125/ABAW-5 .MSC Codes 68T40 Copyright © 2023, 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

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：