检索结果-内蒙古大学图书馆

2023 International Conference on Algorithm, Imaging Processing, and Machine vision, AIPMV 2023

作者： He, Jingze Guo, Yao Song, Qing Department of Computer Science and Technology Tsinghua University Beijing China Pattern Recognition and Intelligent Vision Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781510672444

In this paper, a 3D dangerous goods detection method based on RetinaNet is proposed. This method uses the bidirectional feature pyramid network structure of RetinaNet to extract multi-scale features from point cloud data and trains the system using Focal Loss function to achieve fast and accurate detection of dangerous goods. In addition, in order to improve the detection accuracy, this paper also introduces the 3D region proposal network (3D RPN) and non-maximum suppression (NMS) algorithm. The experimental results show that the proposed method performs well on our self-built CT dataset, with high accuracy and low false positive rate, and is suitable for dangerous goods detection tasks in practical scenarios. © 2024 SPIE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

STRNet:Triple-stream Spatiotemporal Relation Network for Action recognition

引用

International Journal of Automation and computing 2021年第5期18卷 718-730页

作者： Zhi-Wei Xu Xiao-Jun Wu Josef Kittler School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi 214122China Centre for Vision Speech and Signal ProcessingUniversity of SurreyGuildfordGU27XHUK

Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network(ARTNet) and spatiotemporal and motion network(STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network(STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches,which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.

关键词： Action recognition spatiotemporal relation multi-branch fusion long-term representation video classification

来源：评论

学校读者我要写书评

暂无评论

Dual Branch PnP Based Network for Monocular 6D Pose Estimation

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3243-3256页

作者： Jia-Yu Liang Hong-Bo Zhang Qing Lei Ji-Xiang Du Tian-Liang Lin Department of Computer Science and Technology Huaqiao UniversityXiamen361000China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao UniversityXiamen361000China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao UniversityXiamen361000China College of Mechanical Engineering and Automation Xiamen361000China

Monocular 6D pose estimation is a functional task in the field of com-puter vision and *** recent years,2D-3D correspondence-based methods have achieved improved performance in multiview and depth data-based ***,for monocular 6D pose estimation,these methods are affected by the prediction results of the 2D-3D correspondences and the robustness of the per-spective-n-point(PnP)*** is still a difference in the distance from the expected estimation *** obtain a more effective feature representation result,edge enhancement is proposed to increase the shape information of the object by analyzing the influence of inaccurate 2D-3D matching on 6D pose regression and comparing the effectiveness of the intermediate ***,although the transformation matrix is composed of rotation and translation matrices from 3D model points to 2D pixel points,the two variables are essentially different and the same network cannot be used for both variables in the regression ***,to improve the effectiveness of the PnP algo-rithm,this paper designs a dual-branch PnP network to predict rotation and trans-lation ***,the proposed method is verified on the public LM,LM-O and YCB-Video *** ADD(S)values of the proposed method are 94.2 and 62.84 on the LM and LM-O datasets,*** AUC of ADD(-S)value on YCB-Video is *** experimental results show that the performance of the proposed method is superior to that of similar methods.

关键词： 6D pose monocular RGB edge enhancement dual-branch PnP 2D-3D correspondence

来源：评论

学校读者我要写书评

暂无评论

Complexity optimization of adaptive RBF networks

Complexity optimization of adaptive RBF networks

引用

13th International Conference on pattern recognition, ICPR 1996

作者： Leonardis, Aleš Bischof, Horst Department for Pattern Recognition and Image Processing Technical University Vienna Treitlstraße 3/1832 A -1040 Vienna Austria University of Ljubljana Faculty of Computer and Information Science Computer Vision Laboratory Ljubljana Slovenia

ISBN: (纸本)081867282X

We propose an extension of RBF networks which includes a mechanism for optimizing the complexity of the network. The approach involves two procedures: adaptation (training) and selection. The first procedure adaptively changes the locations and the width of the centers of the basis functions and trains the linear weights. The selection procedure performs the elimination of some of the basis functions using an objective function. By iteratively combining these two procedures we achieve a controlled way of training and modifying RBF networks, which balances accuracy, learning time, and complexity of the resulting network. © 1996 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Automatic motion-guided video stylization and personalization 11

Automatic motion-guided video stylization and personalizatio...

引用

19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11

作者： Cao, Chen Chen, Shifeng Zhang, Wei Tang, Xiaoou Shenzhen Key Laboratory for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Information Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781450306164

Video stylization transfers a source video into an artistic version while maintaining temporal coherence between adjacent frames. In this paper, we formulate the unsupervised example-based video stylization with Markov random field model. In our algorithm, we implement an improved optical flow algorithm to maintain temporal coherence while improve the accuracy of estimation along motion boundaries. We also extend our algorithm to the application of video personalization, in which human faces keep clear and distinguishable. A series of techniques are fused in video personalization, including face detection and alignment, motion flow, skin detection, and illumination blending. Given a source video and a style template image, our algorithm produces the stylized and/or personalized video(s) automatically. Experimental results demonstrate that our algorithm performs excellently in both video stylization and personalization. Copyright 2011 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-scale integration with semantic embedding and adaptive excitation transformer for underwater optical image enhancement

引用

Optics and Laser Technology 2025年 189卷

作者： Yang, Jing Liang, Hui Zhu, Shanbing Bai, Shumin Jiang, Fengling Hussain, Amir School of Artificial Intelligence and Big Data Hefei University Hefei230601 China Collaborative Innovation Laboratory for Computer Vision and Pattern Recognition Hefei University Hefei230601 China Hefei Normal University Hefei230601 China School of Computing Edinburgh Napier University Merchiston Campus Scotland EdinburghEH10 5DT United Kingdom

As an important technology in the domains of ocean exploration and underwater robotics, underwater optical image enhancement has drawn significant attention. However, underwater images suffer from severe degradation due to wavelength-related optical attenuation, refraction, and scattering. The need to acquire high-quality underwater optical images poses challenges to current techniques. A dual-branch neural network based on multi-scale integration with semantic embedding and adaptive excitation transformer for underwater optical image enhancement is proposed in this paper. First, a semantic embedding network serving as the semantic branch is introduced to extract low- and high-level semantic features effectively to generate images with clearer edges and texture details. Concurrently, an enhancement branch containing adaptive excitation transformer is constructed to enhance local details while concentrating on global information. Since different feature channels correspond to different patterns of the input image, an adaptive excitation mechanism is deployed to achieve adaptive estimations of channel weights, highlighting the more representative channels while penalizing less important channels to enrich texture and eliminate blurring and color deviations. Additionally, a multi-scale dynamic integration module is designed. It establishes a correlation between the semantic and enhancement branches and adaptively selects prominent features to avoid over-enhancement and improve clarity and color deviation. Both the qualitative and quantitative results evaluated on public underwater optical image datasets show that our method outperforms the state-of-the-art methods in terms of subjective perception and evaluation metrics, indicating outstanding learning and generalization capabilities. Furthermore, excellent performance highlights the substantial benefits it contributes to downstream visual-related engineering tasks. © 2025 Elsevier Ltd

关键词： Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

PON: Proposal Optimization Network for Temporal Action Proposal Generation 16th

PON: Proposal Optimization Network for Temporal Action Propo...

引用

16th International Conference on Intelligent Computing, ICIC 2020

作者： Peng, Xiaoxiao Du, Jixiang Zhang, Hongbo Department of Computer Science and Technology Huaqiao University Quanzhou China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Quanzhou China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Quanzhou China

ISBN: (纸本)9783030607951

Temporal action localization is a challenging task in video understanding. Although great progress has been made in temporal action localization, the most advanced methods still have the problem of sharp performance degradation when an action proposal generated. Most methods use sliding windows method or simply group frames according to frame-level scores. These methods are not enough to provide accurate action boundary and maintain reasonable temporal structure. In order to solve these problems, we propose a novel proposal optimization network to generate start score, end score, action score and regression score, and then remove the redundancy by NMS algorithm. In the proposed method, we introduce a metric loss function to maintain the temporal structure of action proposal in the training process. To verify the effectiveness of the proposed method, we have made comparative experiments on ActivityNet-1.3 dataset respectively, and the proposed method has surpassed some of the state-of-the-art methods on the dataset. © 2020, Springer Nature Switzerland AG.

关键词： Passive optical networks

来源：评论

学校读者我要写书评

暂无评论

Human motion correction and representation method from motion camera

引用

Journal of Engineering 2017年第1期1卷 370-375页

作者： Zhang, Hong-Bo Guo, Feng Zhang, Miaohui Lin, Ying Hsiao, Tsung-Chih Department of Computer Science and Technology Huaqiao University Xiamen China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen China School of Information Science and Engineering Xiamen University Xiamen China Institute of Energy Jiangxi Academy of Sciences Jiangxi Province China

Motion estimation is a basic issue for many computer vision tasks, such as human-computer interaction, motion objection detection and intelligent robot. In many practical scenes, the object movement goes with camera motion. Generally, motion descriptors directly based on optical flow are inaccurate and have low discrimination power. To this end, a novel motion correction method is proposed and a novel motion feature descriptor called the motion difference histogram (MDH) for recognising human action is proposed in this study. Motion estimation results are corrected by background motion estimation and MDH encodes the motion difference between the background and the objects. Experimental results on video shot with camera motion show that the proposed motion correction method is effective and the recognition accuracy of MDH is better than that of the state-of-the-art motion descriptor.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Edge-preserving single image super-resolution 11

Edge-preserving single image super-resolution

引用

19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11

作者： Zhou, Qiang Chen, Shifeng Liu, Jianzhuang Tang, Xiaoou Shenzhen Key Laboratory for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Information Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781450306164

This paper proposes a novel approach to single image super-resolution. First, an image up-sampling scheme is proposed which takes the advantages of both bilateral filtering and mean shift image segmentation. Then we use a shock filter to enhance strong edges in the initial up-sampling result and obtain an intermediate high-resolution image. Finally, we enforce a reconstruction constraint on the high-resolution image so that fine details can be inferred by back projection. Since strong edges in the intermediate result are enhanced, ringing artifacts can be suppressed in the back projection step. We compare our algorithm with several state-of-the-art image super-resolution algorithms. Qualitative and quantitative experimental results demonstrate that our approach performs the best. Copyright 2011 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence Techniques in Diagnosis of Brain Diseases 1

引用

丛书名： SpringerBriefs in Applied Sciences and Technology

1000年

作者： Sasikumar Gurumoorthy Naresh Babu Muppalaneni Xiao-Zhi Gao

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：