检索结果-内蒙古大学图书馆

Proceedings of the 2025 3rd International Conference on Communication Networks and Machine Learning

作者： Zhilong Gao Chunsheng Hua Institute of Intelligent Robots and Pattern Recognition Liaoning University Shenyang Liaoning China College of Information Liaoning University Shenyang Liaoning China

ISBN: (纸本)9798400713231

Challenges in target detection include significant variations in target size, insufficient detection accuracy on small, resource-constrained devices, and the high cost of fully annotating large datasets. To address these issues, a semi-supervised lightweight target detection method based on the improved YOLOv7-tiny algorithm is proposed. First, a new spatial pyramid pooling network, MSPP, is designed to address the problem of significant variations in target size. Then, a lightweight convolutional attention module, GC-SAM, is introduced, which generates stronger feature representations by combining channel and spatial attention mechanisms. Finally, a multi feature semi-supervised data filtering method is proposed, which enhances the model's ability to learn valuable information from unlabeled data, effectively improving detection accuracy. Experimental results show that the improved algorithm achieves a detection accuracy of 82.2% and 63.6% for mAP@50 on 30% of the KITTI and SODA1000 datasets, which is 5.4% and 2.7% higher than the original model, respectively. The model size is only 14.4 MB and the detection speed is 82.1 frames per second, confirming the effectiveness of the algorithm.

关键词： Object Detection

来源：评论

学校读者我要写书评

暂无评论

Visual Prompt Flexible-Modal Face Anti-Spoofing

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2597-2606页

作者： Yu, Zitong Cai, Rizhao Cui, Yawen Liu, Ajian Chen, Changsheng Great Bay University School of Computing and Information Technology Dongguan523000 China Nanyang Technological University ROSE Lab School of EEE 639798 Singapore Hong Kong Polytechnic University Kowloon Hong Kong Chinese Academy of Sciences University of Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Beijing100190 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security College of Electronics and Information Engineering Shenzhen518060 China

Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, multimodal face data collected from the real world is often imperfect due to missing modalities from various imaging sensors. Recently, flexible-modal FAS (Yu et al. 2023) has attracted more attention, which aims to develop a unified multimodal FAS model using complete multimodal face data but is insensitive to test-time missing modalities. In this paper, we tackle one main challenge in flexible-modal FAS, i.e., when missing modality occurs either during training or testing in real-world situations. Inspired by the recent success of the prompt learning in language models, we propose Visual Prompt flexible-modal FAS (VP-FAS), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to downstream flexible-modal FAS task. Specifically, both vanilla visual prompts and residual contextual prompts are plugged into multimodal transformers to handle general missing-modality cases, while only requiring less than 4% learnable parameters compared to training the entire model. Furthermore, missing-modality regularization is proposed to force models to learn consistent multimodal feature embeddings when missing partial modalities. Extensive experiments conducted on two multimodal FAS benchmark datasets demonstrate the effectiveness of our VP-FAS framework that improves the performance under various missing-modality cases while alleviating the requirement of heavy model re-training. © 2004-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

TriFusionNet: Comprehensive Adaptation to Viewpoint Changes and Physiological information Integration in 3D-Based Person Re-Identification 7

TriFusionNet: Comprehensive Adaptation to Viewpoint Changes ...

引用

7th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2024

作者： Hua, Chunsheng Zhang, Wenqian Zhao, Xiaoheng Zhang, Hao Institute Of Intelligent Robots And Pattern Recognition College Of Information Liaoning University Shenyang China

ISBN: (纸本)9798350361445

This study introduces an innovative person re-identification method, TriFusionNet, which cleverly combines 3D reconstruction image features with data augmentation techniques, significantly enhancing performance. We incorporate a 'Physiological information Feature Extraction Branch' to comprehensively capture both the body structure and motion information of persons. The primary challenge addressed is the longstanding negative impact of viewpoint changes on accuracy in person re-identification. Our approach enables the synthesis of more robust and identifiable features in new views. Furthermore, to comprehensively capture person features, we introduce a physiological information feature extraction branch that extracts 15 authentic physiological features from action sequences. These features not only contribute to accuracy but also deepen the understanding of person body status and motion characteristics. The uniqueness of this research lies in going beyond traditional data augmentation methods. Through 3D reconstruction and feature fusion, we address occlusion issues and, through keyframe selection and multi-angle feature fusion, diversify training data more effectively, preserving the body structure and motion information of persons. In summary, TriFusionNet introduces innovative thinking to person re-identification by integrating 3D reconstruction, feature fusion, and physiological information feature extraction. It not only improves performance but also establishes a foundation for more comprehensive extraction of person features, addressing challenges faced by traditional methods. © 2024 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

3D Human Pose Estimation with Bone Symmetry and Motion Locality 3

3D Human Pose Estimation with Bone Symmetry and Motion Local...

引用

3rd International Conference on Electronics and information Technology, EIT 2024

作者： Zhang, Xinyu Hua, Chunsheng Liaoning University Institute of Intelligent Robots and Pattern Recognition College of Information Liaoning Shenyang110036 China

ISBN: (纸本)9798350369151

The bone symmetry and motion locality are two important priors for 3D human pose estimation. For bone symmetry, symmetric bones typically have equal length and higher motion correlation. In terms of motion locality, the motion of the human body conforms to its structure and is temporally continuous. These two priors align with human intuition, but are challenging for Transformer to directly abstract them from data. We propose novel modules, Bone Symmetry Temporal Transformer (BSTT) and Spatial-Temporal Locality Fusion (STLF), to utilize these two priors, and design a new Transformer-based BSMLFormer model. Specifically, BSTT considers the temporal sequences of two symmetric bones as a single new sequence and calculates its global relationships by self-attention mechanism. STLF performs local computations by GCN and convolutions to capture the local dependencies in adjacent joints and adjacent parts. The local-global alternating structure of BSMLFormer allows for consideration of the local information during global calculations. More remarkably, BSMLFormer achieves the state-of-the-art performance with 39.0mm MPJPE on Human3.6M dataset. © 2024 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Approximate computation of Madaline sensitivity based on discrete stochastic technique

引用

Science China(information Sciences) 2010年第12期53卷 2399-2414页

作者： ZHONG ShuiMing , ZENG XiaoQin, LIU HuiYi & XU Yan institute of pattern recognition and intelligent System, college of Computer and information Engineering, Hohai University, Nanjing 210098, China 1. Institute of Pattern Recognition and Intelligent System College of Computer and Information Engineering Hohai University Nanjing 210098 China

The computation of the sensitivity of a Madaline’s output to its parameter perturbation is system- atically discussed. Firstly, according to the discrete feature of Adalines, a method based on discrete stochastic technique is proposed, which derives some analytical formulas for the computation of Adalines’ sensitivity. The method can theoretically solve some problems that are unsolvable by the existing methods based on continu- ous stochastic techniques, release some unpractical constraints, and make it available to theoretically analyze the approximation error of Adalines’ sensitivity. Secondly, on the basis of the sensitivity of Adalines and the structural characteristics of Madalines, a new selection strategy depending on a type of dedication degree for computing Madalines’ sensitivity is proposed, which is superior to current popular way of simply averaging in both precision and complexity. The proposed formulas and algorithm have the advantages of simplicity, low computational complexity, small approximation error, and high generality, as have been verified by a great amount of experimental simulations.

关键词： Adaline Madaline feedforward networks sensitivity parameter perturbation stochastic discrete technique

来源：评论

学校读者我要写书评

暂无评论

Quantization Based Watermarking Methods Against Valumetric Distortions

引用

International Journal of Automation and computing 2017年第6期14卷 672-685页

作者： Zai-Ran Wang Jing Dong Wei Wang College of Engineering and Information Technology University of Chinese Academy of Sciences Center for Research on Intelligent Perception and Computing National Laboratory of Pattern RecognitionInstitute of Automation Chinese Academy of Sciences

Most of the quantization based watermarking algorithms are very sensitive to valumetric distortions, while these distortions are regarded as common processing in audio/video analysis. In recent years, watermarking methods which can resist this kind of distortions have attracted a lot of interests. But still many proposed methods can only deal with one certain kind of valumetric distortion such as amplitude scaling attack, and fail in other kinds of valumetric distortions like constant change attack, gamma correction or contrast stretching. In this paper, we propose a simple but effective method to tackle all the three kinds of valumetric distortions. This algorithm constructs an invariant domain first by spread transform which satisfies certain constraints. Then an amplitude scale invariant watermarking scheme is applied on the constructed domain. The validity of the approach has been confirmed by applying the watermarking scheme to Gaussian host data and real images. Experimental results confirm its intrinsic invariance against amplitude scaling, constant change attack and robustness improvement against nonlinear valumetric distortions.

关键词： Quantization index modulation（QIM） watermarking valumetric distortions amplitude scaling constant change attack

来源：评论

学校读者我要写书评

暂无评论

Steganography algorithm for adaptive multi-rate wideband speech based on algebraic codebook search

引用

The Journal of China Universities of Posts and Telecommunications 2018年第3期25卷 71-79页

作者： Ruan Ye Xu Yanyan Ke Dengfeng Su Kaile School of Information Science and Technology Beijing Forestry University National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences Institute for Integrated and Intelligent Systems Griffith University College of Information Science and Technology Jinan University

With the popularity of adaptive multi-rate wideband （AMR-WB） audio in mobile communication, many AMR- WB based techniques, such as a similar compression architecture to transmit secret information during the process of compression, were proposed to transmit covert messages. However, if a sender does not have the original waveform audio format （WAV） audio, the architecture cannot be used. In this paper, a new covert message method, which takes effect after WAV audio is compressed into AMR-WB speech, is proposed. This method takes advantage of algebraic codebook search. Aiming at improving speed and reducing search space, it does not perform algebraic codebook search using the optimal search algorithm, and it does not reach the positions of non-zero pulses via depth-first tree search that characterizes the energy of audio. According to the features of search methods and the codebook index construction, every track in each subframe is analyzed to find the proper positions for embedding secret information. Experimental results show that the proposed method has satisfactory capacity and simplicity regardless of compression process.

关键词： steganography algorithm WAV audio compressed audio adaptive multi-rate wideband speech

来源：评论

学校读者我要写书评

暂无评论

3D Human Pose Estimation with Bone Symmetry and Motion Locality

3D Human Pose Estimation with Bone Symmetry and Motion Local...

引用

International Conference on Electronics and information Technology (EIT)

作者： Xinyu Zhang Chunsheng Hua Institute of Intelligent Robots and Pattern Recognition College of Information Liaoning University Shenyang China

ISBN: (数字)9798350369151

ISBN: (纸本)9798350369168

关键词： Three-dimensional displays Correlation Computational modeling Pose estimation Stacking Bones Transformers Joints information technology

来源：评论

学校读者我要写书评

暂无评论

AMCF-Net: A Novel Adaptive Multi-Channel Fusion Network for Computer-Aided Diagnosis of Lung Nodules in Chest Computed Tomography

引用

IET Communications 2025年第1期19卷

作者： Nan Wang Yu Gu Lidong Yang Baohua Zhang Jing Wang Xiaoqi Lu Jianjun Li Dahua Yu Ying Zhao Xin Liu Siyuan Tang Qun He Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Digital and Intelligent Industry Inner Mongolia University of Science and Technology Baotou China School of Information and Electronics Beijing Institute of Technology Beijing China College of Information Engineering Inner Mongolia University of Technology Hohhot China School of Computer Science and Technology Baotou Medical College Inner Mongolia University of Science and Technology Baotou China

Malignant lung nodules can significantly affect patients' normal lives and, in severe cases, threaten their survival. Owing to the heterogeneity of computed tomography scans and the varying sizes of nodules, physicians often face challenges in diagnosing this condition. Therefore, a novel adaptive multi-channel fusion network (AMCF-Net) is proposed for computer-aided diagnosis of lung nodules. First, a Multi-Channel Fusion Model module is designed, which divides the channels into two parts in specific proportions, effectively extracting multi-scale channel information while reducing network parameters. After the feature maps output at each layer of the AMCF-Net, a novel adaptive depth-wise separable convolution with a squeeze-and-excitation module is designed to adaptively integrate the feature maps of various stages of the AMCF-Net, ensuring that the key lesions of lung nodules are not lost during classification. Finally, a hybrid loss scheme based on an adaptive mixing ratio is proposed to solve the problem of an imbalanced number of positive and negative nodule samples in the dataset. The model achieved the following test results: an accuracy of 90.22%, a specificity of 98.19%, an F1-score of 86.57%, a sensitivity of 86.49%, and a G-mean of 87.72%. Compared with other advanced networks, AMCF-net delivers high-precision lung nodule classification with minimal inference cost. Related codes have been released at: https://***/GuYuIMUST/AMCF-net .

关键词： computer networks convolution health care image processing neural nets

来源：评论

学校读者我要写书评

暂无评论

TriFusionNet: Comprehensive Adaptation to Viewpoint Changes and Physiological information Integration in 3D-Based Person Re-Identification

TriFusionNet: Comprehensive Adaptation to Viewpoint Changes ...

引用

Advanced Algorithms and Control Engineering (ICAACE), International Conference on

作者： Chunsheng Hua Wenqian Zhang Xiaoheng Zhao Hao Zhang Institute of Intelligent Robots and Pattern Recognition College of Information Liaoning University Shenyang P.R. China

ISBN: (数字)9798350361445

ISBN: (纸本)9798350361452

This study introduces an innovative person re-identification method, TriFusionNet, which cleverly combines 3D reconstruction image features with data augmentation techniques, significantly enhancing performance. We incorporate a “Physiological information Feature Extraction Branch” to comprehensively capture both the body structure and motion information of persons. The primary challenge addressed is the longstanding negative impact of viewpoint changes on accuracy in person re-identification. Our approach enables the synthesis of more robust and identifiable features in new views. Furthermore, to comprehensively capture person features, we introduce a physiological information feature extraction branch that extracts 15 authentic physiological features from action sequences. These features not only contribute to accuracy but also deepen the understanding of person body status and motion characteristics. The uniqueness of this research lies in going beyond traditional data augmentation methods. Through 3D reconstruction and feature fusion, we address occlusion issues and, through keyframe selection and multi-angle feature fusion, diversify training data more effectively, preserving the body structure and motion information of persons. In summary, TriFusionNet introduces innovative thinking to person re-identification by integrating 3D reconstruction, feature fusion, and physiological information feature extraction. It not only improves performance but also establishes a foundation for more comprehensive extraction of person features, addressing challenges faced by traditional methods.

关键词： Three-dimensional displays Control engineering Training data Feature extraction Data augmentation Physiology Data mining

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：