检索结果-内蒙古大学图书馆

Environment Adaptive Deep Learning Classification System Based on One-shot Guidance

computers, Materials & Continua 2022年第12期73卷 5185-5196页

作者： Guanghao Jin Chunmei Pei Na Zhao Hengguang Li Qingzeng Song Jing Yu School of Telecommunication Engineering Beijing PolytechnicBeijing100176China Department of Mathematics Wayne State UniversityDetroit48202MIUSA School of Computer Science and Technology Tiangong UniversityTianjin300387China

When utilizing the deep learning models in some real applications,the distribution of the labels in the environment can be used to increase the ***,to compute this distribution,there should be the validation set that is labeled by the ground *** the other side,the dependency of ground truths limits the utilization of the distribution in various *** this paper,we carried out a novel system for the deep learning-based classification to solve this ***,our system only uses one validation set with ground truths to compute some hyper parameters,which is named as one-shot ***,in an environment,our system builds the validation set and labels this by the prediction results,which does not need any guidance by the ground ***,the computed distribution of labels by the validation set selectively cooperates with the probability of labels by the output of models,which is to increase the accuracy of predict results on testing *** selected six popular deep learning models on three real datasets for the *** experimental results show that our system can achieve higher accuracy than state-of-art methods while reducing the dependency of labeled validation set.

关键词： Deep learning classification distribution of labels probability of labels

来源：评论

学校读者我要写书评

暂无评论

Pose-guided feature region-based fusion network for occluded person re-identification

Pose-guided feature region-based fusion network for occluded...

引用

作者： Xie, Gengsheng Wen, Xianbin Yuan, Liming Wang, Jianchen Guo, Changlun Jia, Yansong Li, Minghao School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China

Learning distinguishing features from training datasets while filtering features of occlusions is critical to person retrieval scenarios. Most of the current person re-identification (Re-ID) methods based on classification or deep metric representation learning tend to overlook occlusion issues on the training set. Such representations from obstacles are easily over-fitted and misleading due to being considered as a part of the human body. To alleviate the occlusion problem, we propose a pose-guided feature region-based fusion network (PFRFN), to utilize pose landmarks as guidance to guide local learning for a good property of local feature, and the representation learning risk is evaluated on each part loss separately. Compared with only using global classification loss, concurrently considering local loss and the results of robust pose estimation enable the deep network to learn the representations of the body parts that prominently displayed in the image and gain the discriminative faculties on occluded scenes. Experimental results on multiple datasets, i.e., Market-1501, DukeMTMC, CUHK03, demonstrate the effectiveness of our method in a variety of scenarios. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Detached and Interactive Multimodal Learning 24

Detached and Interactive Multimodal Learning

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Fan, Yunfeng Xu, Wenchao Wang, Haozhao Liu, Junhong Guo, Song Department of Computing The Hong Kong Polytechnic University Hong Kong Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Hubei China School of Software Beihang University Beijing China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong

ISBN: (纸本)9798400706868

Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data. However, traditional MML methods generally use the joint learning framework with a uniform learning objective that can lead to the modality competition issue, where feedback predominantly comes from certain modalities, limiting the full potential of others. In response to this challenge, this paper introduces DI-MML, a novel detached MML framework designed to learn complementary information across modalities under the premise of avoiding modality competition. Specifically, DI-MML addresses competition by separately training each modality encoder with isolated learning objectives. It further encourages cross-modal interaction via a shared classifier that defines a common feature space and employing a dimension-decoupled unidirectional contrastive (DUC) loss to facilitate modality-level knowledge transfer. Additionally, to account for varying reliability in sample pairs, we devise a certainty-aware logit weighting strategy to effectively leverage complementary information at the instance level during inference. Extensive experiments conducted on audio-visual, flow-image, and front-rear view datasets show the superior performance of our proposed method. The code is released at https://***/fanyunfeng-bit/DI-MML. © 2024 Owner/Author.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Alignment efficient image-sentence retrieval considering transferable cross-modal representation learning

引用

Frontiers of computer science 2024年第1期18卷 77-91页

作者： Yang YANG Jinyi GUO Guangyu LI Lanyu LI Wenjie LI Jian YANG School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Department of Computing Hong Kong Polytechnic UniversityHong Kong 100872China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing 210094China 14th Research Institute of China Electronics Technology Group Corporation Nanjing 210094China guangyu.li2017@***

Traditional image-sentence cross-modal retrieval methods usually aim to learn consistent representations of heterogeneous modalities,thereby to search similar instances in one modality according to the query from another modality in *** basic assumption behind these methods is that parallel multi-modal data(i.e.,different modalities of the same example are aligned)can be obtained in *** other words,the image-sentence cross-modal retrieval task is a supervised task with the alignments as ***,in many real-world applications,it is difficult to realign a large amount of parallel data for new scenarios due to the substantial labor costs,leading the non-parallel multi-modal data and existing methods cannot be used *** the other hand,there actually exists auxiliary parallel multi-modal data with similar semantics,which can assist the non-parallel data to learn the consistent ***,in this paper,we aim at“Alignment Efficient Image-Sentence Retrieval”(AEIR),which recurs to the auxiliary parallel image-sentence data as the source domain data,and takes the non-parallel data as the target domain *** single-modal transfer learning,AEIR learns consistent image-sentence cross-modal representations of target domain by transferring the alignments of existing parallel ***,AEIR learns the image-sentence consistent representations in source domain with parallel data,while transferring the alignment knowledge across domains by jointly optimizing a novel designed cross-domain cross-modal metric learning based constraint with intra-modal domain adversarial ***,we can effectively learn the consistent representations for target domain considering both the structure and semantic ***,extensive experiments on different transfer scenarios validate that AEIR can achieve better retrieval results comparing with the baselines.

关键词： image-sentence retrieval transfer learning semantic transfer structure transfer

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Joint Service Placement and Request Scheduling in Mobile Edge Computing Networks 28

Deep Reinforcement Learning for Joint Service Placement and ...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Deng, Yuxuan Li, Xiuhua Sun, Chuan Hao, Jinlong Wang, Xiaofei Leung, Victor C. M. School of Big Data and Software Engineering Chongqing University Chongqing China Chongqing Changan Automobile Software Technology Co. Ltd Chongqing China TKLAN College of Intelligence and Computing Tianjin University Tianjin China College of Computer Science and Software Engineering Shenzhen University Shenzhen China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798350300482

Mobile edge computing aims to provide cloud-like services on edge servers located near Mobile Devices (MDs) with higher Quality of Service (QoS). However, the mobility of MDs makes it difficult to find a global optimal solution for the coupled service placement and request scheduling problem. To address these issues, we consider a three-Tier MEC network with vertical and horizontal cooperation. Then we formulate the joint service placement and request scheduling problem in a mobile scenario with heterogeneous services and resource limits, and convert it into two Markov decision processes to decouple decisions across successive time slots. We propose a Cyclic Deep Q-network-based Service placement and Request scheduling (CDSR) framework to find a long-Term optimal solution despite future information unavailability. Specifically, to solve the issue of enormous action space, we decompose the system agent and train them cyclically. Evaluation results demonstrates the effectiveness of our proposed CDSR on user-perceived QoS. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Light field super-resolution using complementary-view feature attention

引用

Computational Visual Media 2023年第4期9卷 843-858页

作者： Wei Zhang Wei Ke Da Yang Hao Sheng Zhang Xiong Faculty of Applied Sciences Macao Polytechnic UniversityMacao SAR 999078China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191Chinaand Beihang Hangzhou Innovation Institute YuhangXixi Octagon CityYuhang DistrictHangzhou 310023China

Light field(LF)cameras record multiple perspectives by a sparse sampling of real scenes,and these perspectives provide complementary *** information is beneficial to LF super-resolution(LFSR).Compared with traditional single-image super-resolution,LF can exploit parallax structure and perspective correlation among different LF ***,the performance of existing methods are limited as they fail to deeply explore the complementary information across LF *** this paper,we propose a novel network,called the light field complementary-view feature attention network(LF-CFANet),to improve LFSR by dynamically learning the complementary information in LF ***,we design a residual complementary-view spatial and channel attention module(RCSCAM)to effectively interact with complementary information between complementary ***,RCSCAM captures the relationships between different channels,and it is able to generate informative features for reconstructing LF images while ignoring redundant ***,a maximum-difference information supplementary branch(MDISB)is used to supplement information from the maximum-difference angular positions based on the geometric structure of LF *** branch also can guide the process of *** results on both synthetic and real-world datasets demonstrate the superiority of our *** proposed LF-CFANet has a more advanced reconstruction performance that displays faithful details with higher SR accuracy than state-of-the-art methods.

关键词： light field(LF) super-resolution(SR) attention

来源：评论

学校读者我要写书评

暂无评论

3D Gaze Estimation via Binocular Disparity and Feature Refinement 10

3D Gaze Estimation via Binocular Disparity and Feature Refin...

引用

10th International Conference on Big Data Computing and Communications, BIGCOM 2024

作者： Wang, Chengxin Chen, Qiuxia Tian, Ying Yang, Jinfeng School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic Shenzhen China

ISBN: (纸本)9798331509538

The eyes are the windows to the soul and are crucial for studying human behavior. Therefore, gaze estimation has attracted much attention in the field of computer vision. In recent years, convolutional neural networks have driven significant progress in gaze estimation research. Despite the remarkable achievements of gaze technology based on full-face images, the inability to obtain full-face images in specific scenarios makes research based on eye images particularly important. This paper proposes a three-dimensional gaze estimation model that takes binocular images as input, using VGG16 as the backbone network for feature extraction. To enhance the feature extraction capability, we have embedded channel attention and spatial attention mechanisms. Meanwhile, to improve the stability of gaze estimation, we classify real gaze angles. First, we perform a preliminary screening of gaze direction through a classification task, and then perform linear regression with the true angle. Finally, we optimize gaze features using binocular vision differences to finetune the gaze estimator. Experiments have shown that our method performs well on three public datasets. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy Efficiency in WSNs with Hybrid LEACH-D and ANN

Enhancing Energy Efficiency in WSNs with Hybrid LEACH-D and ...

引用

2024 Multimedia university engineering Conference, MECON 2024

作者： Qamar, Muhammad Salman Haq, Ihsan Ul Munir, Muhammad Fahad Roslee, Mardeni Bin Awan, Adnan Anwar Waseem, Athar International Islamic University Department of Electrical and Computer Engineering Islamabad Pakistan Multimedia University Centre for Wireless Technology Faculty of Engineering Cyberjaya63100 Malaysia School of Engineering California Polytechnic State University Department of Computer Science and Software Engineering San Luis ObispoCA United States

ISBN: (纸本)9798331530747

This paper explores strategies to improve the energy efficiency and operational longevity of Wireless Sensor Networks (WSNs) through the optimization of clustering techniques and energy efficient routing protocols. The proposed methodology is precisely crafted to optimize energy consumption (EC) while preserving the overall effectiveness of WSNs. LEACH (Low Energy Adaptive Cluster Hierarchy) is a cluster-based protocol where non-cluster head nodes deactivate their RF until their allocated time slots. Nevertheless, a drawback of traditional LEACH is its random rotation of local Cluster Heads (CH), leading to unequal cluster distribution. To overcome this issue, we proposed a novel hybrid technique called LEACH-D protocol and Artificial Neural Network (ANN). The LEACH-D algorithm enhances the duration of transmission tasks while ensuring uniform battery energy consumption. On the other hand, the ANN plays a pivotal role in coordinating optimal routing decisions and CH placement, refining data aggregation and transmission mechanisms to restrain idle listening. The findings indicate that the suggested approach manifests as substantial reductions in energy consumption and prolonged network lifespan of WSN. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

An effective fault localization approach for Verilog based on enhanced contexts

引用

Frontiers of computer science 2024年第5期18卷 223-225页

作者： Zhuo ZHANG Ya LI Lei XIA Jianxin XUE Jiang WU Xiaoguang MAO School of Computer Science and Engineering Xi'an University of TechnologyXi'an 710048China Ningbo Artificial Intelligence Institute Shanghai Jiao Tong UniversityNingbo 315000China No.83 Army Joint and Truma Disease Treatment Centre of PLA Xinxiang 453000China Department of Software Engineering Shanghai Second Polytechnic UniversityShanghai 201209China College of Computer National University of Defense TechnologyChangsha 410073China

New computer architecture innovationswith diverse functionalities and comprehensive features continue to emerge incessantly,resulting in a rising trend of incorporating a larger number of circuit devices into these products[1].In the case of a sophisticated and expansive integrated circuit chip,the presence of defective or malfunctioning components can significantly impact the overall performance of the *** situation may even result in costly repercussions.

关键词： Verilog computer circuit.

来源：评论

学校读者我要写书评

暂无评论

Heterologous Image Matching Based on Salience Region Using Q-test and Kernel Density Estimation 4

Heterologous Image Matching Based on Salience Region Using Q...

引用

4th International Conference on computer Vision and Pattern Analysis, ICCPA 2024

作者： Zhai, Jinlong Yan, Xiaohu Xu, Yang School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-MacaoGreater Bay Area Shenzhen Polytechnic University Shenzhen518055 China

ISBN: (纸本)9781510682528

To address the matching problem caused by the salience differences in spatial features, spectrum and contrast between heterologous images, a heterologous image matching method based on salience region using Q-test and kernel density estimation is proposed in this paper. Firstly, the center pixel point of each sub-region in the image is detected for salience difference with other points in its neighborhood by using the Q-test method. The detected points are defined as Q-points. Secondly, the point with the largest kernel density in all Q-points is calculated by using kernel density estimation function and defined as the M-point. Then, the region size is defined according to the coordinates of M-point, and the salience region is detected. Finally, to comprehensively evaluate the performance of the proposed method, five common types of heterologous images are selected as data sources, including point cloud depth maps, infrared images, electronic navigational maps, synthetic aperture radar images, and night-time light images. Based on the salience regions, comparative experiments are carried out using histogram of absolute phase consistency gradients (HAPCG) and histogram of the orientation of the weighted phase descriptor (HOWP). The results show that the matching performance of the proposed method is better than that of the original algorithm without salience region, especially on the type of electronic navigational map. © 2024 SPIE.

关键词： Radar imaging

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：