检索结果-内蒙古大学图书馆

2021 2nd International Workshop on Electronic communication and Artificial Intelligence, IWECAI 2021

作者： Zhao, Zhengyun Yang, Qingpeng Yang, Shangqin Wang, Jun School of Artificial Intelligence Henan University Kaifeng Henan475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng Henan475004 China

Depth modal features can provide complementary information for salient object detection (SOD). Most of the existing RGB-D SOD methods focus on fully combining RGB and Depth modal features without distinguishing them. In this paper, we propose a new depth guided cross-modal residual adaptive network for RGB-D SOD. We use two independent resnet-50 to extract the features of the two modes respectively. Then the cross-modal channel-wise refinement module is designed to obtain complementary modal information. We design a crossmodal guided module to make complementary modal information guide RGB image feature extraction. Finally, the residual adaptive selection module is used to enhance the spatial mutual concerns between the two modal features to achieve multimodal information fusion. Experimental results show that our method can achieve a more reasonable fusion state of RGB and Depth, and verify the effectiveness of our final saliency model. © Published under licence by IOP Publishing Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PRM: Pose Recalibration Module for Action Recognition

PRM: Pose Recalibration Module for Action Recognition

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2021

作者： Tian, Guixiong Yi, Yang Meng, Zijian Li, Zhonghong Song, Jialun School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangzhou Xinhua University Guangzhou China Guangdong Province Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (纸本)9789811669620

Two-stream convolutional network is the mainstream method of human action recognition, which can achieve excellent recognition precision in most datasets. However, the challenge of two-stream convolutional network is that it can not model human action well. To tackle this issue, this paper proposes Pose Recalibration Module (PRM) to better model human action features. The proposed PRM is composed of three components: (1) Part Affinity Fields pose estimator Module to explicitly capture human actions and generate human joint heatmap, (2) Multi-scale Action Extraction Module to construct different scales of joint heatmap sequence at different time intervals, and (3) Action Classification Module to classify action. Finally, this paper arranges late fusion strategy to fuse pose modalities and the two-stream network to obtain the final classification score. Experimental results on UCF101 and HMDB51 show that our approach can boost the performance of two-stream network. Meanwhile, our method obtains a competitive performance compared with state-of-the-art methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Addr-Net: Attention Mechanism-Based Dual-Stream Deformable Medical Image Registration Network

SSRN

引用

SSRN 2024年

作者： Fan, Chao Zhu, Xinru Peng, Bincheng Xuan, Zhihui Zhu, Zhentong School of Artificial Intelligence and Big Data Henan University of Technology Henan Province Zhengzhou City China Key Laboratory of Grain Information Processing and Control Ministry of Education Henan Province Zhengzhou City China School of Information Science and Engineering Henan University of Technology Henan Province Zhengzhou City450001 China

Medical image registration is crucial for tumor growth monitoring, radiation therapy, and disease diagnosis. Recently, U-Net type networks have become widely used in unsupervised image registration to predict dense deformation fields. However, for image data with large deformations, these networks are prone to interference from outliers and task-irrelevant regions, leading to suboptimal registration accuracy and difficulty in maintaining the continuity of the deformation field. To address this issue, we propose a novel model called ADDR-Net. ADDR-Net leverages dual encoders and incorporates a Cross-Perceptual Attention Module (CPA) alongside a Multi-dimensional Attention Module (MDA) to enhance registration. Unlike traditional methods that concatenate fixed and moving images into a single encoder, ADDR-Net uses dual encoders to separately extract features from each image, facilitating explicit feature matching between image pairs. The CPA module, embedded within the encoder, enhances the extraction of global features over long distances. Meanwhile, the MDA module, embedded within the skip connection, filters redundant features and extracts local refined features, thereby improving the U-shaped network architecture. Experimental results demonstrate that ADDR-Net outperforms state-of-the-art methods. Specifically, compared to the Transformer-based TransMorph method, ADDR-Net increases the Dice scores on two publicly available brain datasets, IXI and OASIS, by 1.4% and 3.5%, respectively. © 2024, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A Review of Detection-Related Multiple Object Tracking in Recent Times

A Review of Detection-Related Multiple Object Tracking in Re...

引用

International Conference on Advanced Communication Technology (ICACT)

作者： Suya Li Ying Cao Xin Xie Henan University School of Computer and Information Engineering Jinming Campus Kaifeng China School of Computer and Information Engineering Jinming Campus Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China

Multi-object tracking (MOT) is garnering more attention due to its widespread application in the area of autonomous driving, human-computer interaction, and intelligent video surveillance. Especially in recent years, MOT has rapidly developed thanks to related technologies such as object detection, which has helped in handling interfering factors such as crowded scene occlusion, small objects, and similar appearances. Among these, Detection-based MOT is the mainstream for accurately forming objects' trajectories. Therefore, according to the analysis of the last three years' research, this paper particularly focuses on discussing the continuous optimization strategies of MOT around the development of object detection at each stage. In addition, this article also introduces the commonly used benchmark datasets and related applications of MOT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Object Tracking Methods Based on Deep Learning

A Survey of Object Tracking Methods Based on Deep Learning

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2021

作者： Yi, Yang Meng, Zijian Tian, Guixiong School of Data and Computer Science Sun Yat-sen University Guangzhou China School of Information Science Xinhua College of Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (纸本)9789811669620

The object tracking problem is usually represented as estimating the state of an arbitrary target in a video only given its state in the initial frame. Many recent object tracking methods based on deep learning have achieved advanced performance. In general, most object tracking methods can be divided into two types. One family of trackers such as DiMP, ATOM learn a discriminative classifier, which adopt online updating strategy, to distinguish the target object from the background. In the process of tracking, these methods need to update the model parameters using reference frames and states. The other family of trackers represented by Siamese network use the reference state and the current frame as the input of the model without changing or updating the parameters. These trackers calculate the cross-corrlation between the reference frame and the current frame to complete the object tracking task. Both methods usually divide object tracking task into two subtasks: classification and estimation. The target location is maintained by target classification, and the accurate target boundary box is obtained by target estimation. In this paper, we will investigate some state-of-the-art object tracking methods using deep learning in recent years. These methods will be introduced in three different emphases: classification, estimation, both. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification

arXiv

引用

arXiv 2024年

作者： Liu, Chun Yang, Longwei Dong, Dongmei Li, Zheng Yang, Wei Han, Zhigang Wang, Jiayao School of Computer and Information Engineering Henan Key Laboratory of Big Data Analysis and Processing Henan Engineering Laboratory of Spatial Information Processing Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China Beijing Electro-Mechanical Engineering Institute Beijing100074 China College of Geography and Environmental Science Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China

Few-shot hyperspectral image classification aims to identify the classes of each pixel in the images by only marking few of these pixels. And in order to obtain the spatial-spectral joint features of each pixel, the fixed-size patches centering around each pixel are often used for classification. However, observing the classification results of existing methods, we found that boundary patches corresponding to the pixels which are located at the boundary of the objects in the hyperspectral images, are hard to classify. These boundary patchs are mixed with multi-class spectral information. Inspired by this, we propose to augment the prototype network with TransMix for few-shot hyperspectrial image classification(APNT). While taking the prototype network as the backbone, it adopts the transformer as feature extractor to learn the pixel-to-pixel relation and pay different attentions to different pixels. At the same time, instead of directly using the patches which are cut from the hyperspectral images for training, it randomly mixs up two patches to imitate the boundary patches and uses the synthetic patches to train the model, with the aim to enlarge the number of hard training samples and enhance their diversity. And by following the data agumentation technique TransMix, the attention returned by the transformer is also used to mix up the labels of two patches to generate better labels for synthetic patches. Compared with existing methods, the proposed method has demonstrated sate of the art performance and better robustness for few-shot hyperspectral image classification in our experiments. All the codes are available at https://***/HENULWY/APNT. Copyright © 2024, 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

An application-oriented multi-granularity vehicle trajectory data indexing structure based on concept lattice 5

An application-oriented multi-granularity vehicle trajectory...

引用

5th International Conference on Computer Information Science and Application Technology, CISAT 2022

作者： Xu, Tao Zhang, Zixiang Ma, Xiaqing Deng, Jiaming Zhao, Yingying Li, Xiang Key Laboratory of Geographical Information Science Ministry of Education East China Normal University Shanghai200241 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China School of Computer and Information Engineering Henan University Kaifeng475004 China International Education College Henan University Zhengzhou450046 China Henan Technology Innovation Center of Spatio-Temporal Big Data Henan University Zhengzhou450046 China Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China

ISBN: (纸本)9781510660076

Massive amount of vehicle trajectory data is an important data source and has been widely used in many research fields. However, due to the huge volume and variety of application scenarios, it is still not easy to achieve the application-oriented and efficient retrieval of vehicle trajectory. The paper proposes a multi-granularity vehicle trajectory index method based on the concept lattice model. The method identifies the multi-granularity feature regions for application requirements to segment vehicle trajectory and employs the concept lattice model to maintain the complex relationships between vehicle trip and the feature regions, to realize the vehicle travel trajectory data retrieval for the multi-granularity feature regions. In this experiment, shanghai city is divided into 21 feature regions according to the county-level area of Shanghai, and the concept lattice index structure of vehicle trips is constructed. The availability and efficiency of the proposed method are verified by the comparative experimental results. © 2022 SPIE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-level Cross-modal Feature Alignment via Contrastive Learning towards Zero-shot Classification of Remote Sensing Image Scenes

arXiv

引用

arXiv 2023年

作者： Liu, Chun Ma, Suqiang Li, Zheng Yang, Wei Han, Zhigang School of Computer and Information Engineering Henan Key Laboratory of Big Data Analysis and Processing Henan Engineering Laboratory of Spatial Information Processing Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China College of Geography and Environmental Science Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China

Zero-shot classification of image scenes which can recognize the image scenes that are not seen in the training stage holds great promise of lowering the dependence on large numbers of labeled samples. To address the zero-shot image scene classification, the cross-modal feature alignment methods have been proposed in recent years. These methods mainly focus on matching the visual features of each image scene with their corresponding semantic descriptors in the latent space. Less attention has been paid to the contrastive relationships between different image scenes and different semantic descriptors. In light of the challenge of large intra-class difference and inter-class similarity among image scenes and the potential noisy samples, these methods are susceptible to the influence of the instances which are far from these of the same classes and close to these of other classes. In this work, we propose a multi-level cross-modal feature alignment method via contrastive learning for zero-shot classification of remote sensing image scenes. While promoting the single-instance level positive alignment between each image scene with their corresponding semantic descriptors, the proposed method takes the cross-instance contrastive relationships into consideration, and learns to keep the visual and semantic features of different classes in the latent space apart from each other. Extensive experiments have been done to evaluate the performance of the proposed method. The results show that our proposed method outperforms state of the art methods for zero-shot remote sensing image scene classification. All the code and data are available at github https://***/masuqiang/MCFA-Pytorch. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Node Classification on Attributed Networks Based on Prototypical Network

Few-Shot Node Classification on Attributed Networks Based on...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yaliang Zhao Guangming Zhang Jinke Wang Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng China

In today’s society, the interactions between various entities form complicated attributed networks. The node classification task as the core task of analyzing attribute networks has gained a considerable amount of attention from researchers. The existing graph neural network-based node classification approaches all demand lots of labeled data, but a high percentage of node classes in practical scenarios contain only restricted labeled data. So their classification effect is not good. In response to this problem, we put forward an improved graph prototypical network (IGPN) to enhance the few-shot node classification’s accuracy. In particular, we start by obtaining the embedding representations of nodes on the attributed network through a graph attention network. Then combined with the node’s degree information and neighbor information, the importance coefficient of all nodes in the support set is learned. After that, we can obtain the prototype representation of every class. Finally, the node classification can be completed by the distance of the query nodes’ representation from all class prototypes. Our method is preferable to the baseline method on three datasets according to a large number of experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TPE-H2MWD:an exact thumbnail preserving encryption scheme with hidden Markov model and weighted diffusion

引用

Frontiers of Information Technology & Electronic Engineering 2023年第8期24卷 1169-1180页

作者： Xiuli CHAI Xiuhui CHEN Yakun MA Fang ZUO Zhihua GAN Yushu ZHANG School of Artificial Intelligence Henan Engineering Research Center for Industrial Internet of ThingsHenan UniversityZhengzhou450046China Henan Key Laboratory of Cyberspace Situation Awareness Zhengzhou450001China School of Software Intelligent Data Processing Engineering Research Center of Henan ProvinceInstitute of Intelligent Network SystemHenan UniversityKaifeng475004China College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing211106China

With the substantial increase in image transmission,the demand for image security is ***-like images can be obtained by conventional encryption schemes,and although the security of the images can be guaranteed,the noise-like images cannot be directly previewed and *** on the rank-then-encipher method,some researchers have designed a three-pixel exact thumbnail preserving encryption(TPE2)scheme,which can be applied to balance the security and availability of images,but this scheme has low encryption *** this paper,we introduce an efficient exact thumbnail preserving encryption ***,blocking and bit-plane decomposition operations are performed on the plaintext *** zigzag scrambling model is used to change the bit positions in the lower four bit ***,an operation is devised to permute the higher four bit planes,which is an extended application of the hidden Markov ***,according to the difference in bit weights in each bit plane,a bit-level weighted diffusion rule is established to generate an encrypted image and still maintain the same sum of pixels within the *** results show that the proposed scheme improves the encryption efficiency and can guarantee the availability of images while protecting their privacy.

关键词： Hidden Markov model Weighted diffusion Balance between usability and privacy Image encryption

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：