检索结果-内蒙古大学图书馆

International Conference on Systems and Informatics (ICSAI)

作者： Jie Li Jie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665426251

In view of the wide variety of plants on the earth, the plant species identification is particularly necessary to protect and preserve biodiversity. In this work, we propose a plant image classification method based on the encoder-decoder model with additive attention mechanism to extract plant image features and convert them into text descriptions related to plant features. In a well-trained network, it can successfully classify on the species of the generated plant texts. We show that, the proposed method not only equalizes the results of deep convolutional neural network on classification task, but also uses of the prior information of botanists in classification, and thus provide a significant prediction result.

关键词： Earth image recognition Text recognition Biological system modeling Feature extraction Convolutional neural networks Biodiversity

来源：评论

学校读者我要写书评

暂无评论

New Traveling Wave Solutions and Dynamic Behavior Analysis of the Nonlinear Rangwala-Rao Model

SSRN

引用

SSRN 2023年

作者： Peng, Chen Li, Zhao College of Computer Science Chengdu University Chengdu610106 China Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu University 610106 China

This work investigates the nonlinear Rangwala-Rao equation, which stems from the mixed derivative nonlinear Schrödinger equation. For retrieving new exact solutions to the equation, the complete discriminant system for polynomial method is employed. In results, some novel traveling wave solutions, including solitary wave solutions, triangular function solutions, periodic solutions and Jacobi elliptic function solutions are obtained and demonstrated through numerical simulations. The bifurcations of phase portraits of the traveling wave solutions are depicted to reveal the dynamic behavior of the Rangwala-Rao equation using the qualitative theory of dynamical systems. Furthermore, considering external perturbation, the chaotic motions of the perturbed Rangwala-Rao equation are investigated. © 2023, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Indoor Elderly Fall recognition System Based on Target Detection and Self-attention Model 2

Indoor Elderly Fall Recognition System Based on Target Detec...

引用

2nd International Conference on Electronics, Communications and Information Technology, CECIT 2021

作者： Liu, Min Ling, Xufeng Yang, Jie School of Health Tianhua College Shanghai Normal University Shanghai China AI School Tianhua College Shanghai Normal University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China

ISBN: (纸本)9781665437578

With the increasing aging of the society, a series of consequences caused by falls of the elderly have become a serious medical problem and a real social problem. Aiming at the fall behavior of the elderly, the research and development of human fall recognition technology has practical application value. This paper proposes a method to recognize human targets in indoor images using target detection technology, and then use the trained neural network based on Self-attention technique named Vision Transformer (ViT) to recognize the falling posture of the elderly. Firstly, the target detection model is optimized and trained for indoor scene, so that the model can accurately detect human targets in indoor scene;Next, the indoor scene human target image is preprocessed, and the indoor human pose image data set is constructed;Then, the data set is used to train the ViT depth network, and enable it to correctly classify five postures (standing, sitting, lying, bending and crawling). The experimental results show that ViT network achieves high accuracy and excellent generalization capacity for the above 5 human posture and can realize the recognition of elderly falls. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection 39

Provable Discriminative Hyperspherical Embedding for Out-of-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zou, Zhipeng Wan, Sheng Li, Guangyu Han, Bo Liu, Tongliang Zhao, Lin Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Hong Kong Baptist University China Sydney AI Centre The University of Sydney Sydney Australia Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Out-of-distribution (OOD) detection aims to identify the test examples that do not belong to the distribution of training data. The distance-based methods, which identify OOD examples based on their distances from the centroids of in-distribution (ID) examples, have demonstrated promising OOD detection performance. However, the objectives utilized in prior approaches are typically designed for classification and thus might not yield sufficient discriminative power to distinguish between ID and OOD examples. Therefore, this paper proposes a prototype-based contrastive learning framework for OOD detection, which is termed provable Discriminative Hyperspherical Embedding (DHE). The proposed framework provides a theoretical analysis of inter-class dispersion, which is proved to be fundamental in reducing the false positive rate (FPR) on OOD examples. Based on this, we devise an angular spread loss to achieve the maximal dispersion of the prototypes of different classes prior to training. Subsequently, a prototype-enhanced contrastive loss is introduced to align embeddings of ID examples closely with their corresponding prototypes. In our proposed DHE, the maximal prototype dispersion is theoretically proved, thereby avoiding the pitfalls of local optima commonly encountered by most existing methods. Experimental results demonstrate the effectiveness of our proposed DHE, which showcases a remarkable reduction in FPR95 (i.e., 5.37% on CIFAR-100) and more than doubling the computational efficiency when compared with the state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Thermal-Torsion Coupling Loading Analysis and Optimization of 3D PoP Assembly Solder Joints at Different Temperatures

引用

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Gao, Chao Huang, Chunyue Liang, Yin Dian, Chen Lan, Jingyi Wang, Gui Guilin University of Electronic Technology School of Electrical and Mechanical Engineering Guilin541004 China Chengdu University Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu610106 China Chengdu Aeronautic Vocational and Technical College Chengdu610021 China

A simulation analysis was conducted to investigate the stress distribution of Package-on-Package (PoP) assembly array solder joints subjected to thermal-torsional coupling loads, with the validity of the simulation confirmed through coupled loading stress-strain measurement experiments. The volume-weighted average method was employed to calculate the average equivalent stress (Δσ) of the critical solder joint danger element layer within the PoP assembly array, using Δσ as the evaluation benchmark. The impact and sensitivity of structural parameters on the thermal-torsional coupling stress of solder joints were examined. A structural parameter sensitivity model was developed to facilitate the stability and optimization analysis of the structural parameter intervals. The results indicate that solder joints in the lower array of the PoP assembly experience higher thermal-torsional coupling stress, with the peak internal stress occurring at the interface between the solder joint and the copper pad. The variation in thermal-torsional coupling stress of the array solder joints is more pronounced in the low-temperature region compared to the high-temperature region, with maximum stress occurring at -55°C and minimum stress observed at 125°C. Within the structural parameter range, the Δσ value of the critical solder joint shows a negative correlation with solder joint height, solder joint diameter, and substrate thickness, and a positive correlation with PCB thickness. The sensitivity to structural parameters follows the order: solder joint diameter, solder joint height, PCB thickness, and substrate thickness. Finally, the optimal range of structural parameters was determined, and the stability of this range was assessed. © 2011-2012 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic Effects on Traveling Wave Solutions of the Space-Fractional Long-Short-Wave Interaction System with Multiplicative White Noise

SSRN

引用

SSRN 2023年

In this paper, the stochastic space-fractional long-short-wave interaction system (SF-LSWIS) with multiplicative white noise is considered. The stochastic exact solutions including triangular function solutions, hyperbolic function solutions as well as Jacobian elliptic function solutions are obtained via complete discriminant system for polynomial method. For this purpose, the traveling wave transformation is applied to carry out the ordinary differential equation of this model, which is also converted to a dynamical system. Thereafter, Qualitative behavior, bifurcation of the phase portraits and chaotic behaviors of the system are studied. Furthermore, the 3D surface, graphs of contour plots and level curves of some exact solutions are depicted by choosing proper parameter values. The influence and effect of fractional derivative and the noise strength on the solutions are also studied. © 2023, The Authors. All rights reserved.

关键词： Hyperbolic functions

来源：评论

学校读者我要写书评

暂无评论

SLoRD: Structural Low-Rank Descriptors for Shape Consistency in Vertebrae Segmentation

引用

IEEE journal of biomedical and health informatics 2025年 PP卷 PP页

作者： Xin You Yixin Lou Minghui Zhang Jie Yang Yun Gu Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai200240 China

Automatic and precise multi-class vertebrae segmentation from CT images is crucial for various clinical applications. However, due to similar appearances between adjacent vertebrae and the existence of various pathologies, existing single-stage and multi-stage methods suffer from imprecise vertebrae segmentation. Essentially, these methods fail to explicitly impose both contour precision and intra-vertebrae voxel consistency constraints synchronously, resulting in the intra-vertebrae segmentation inconsistency, which refers to multiple label predictions inside a singular vertebra. In this work, we intend to label complete binary masks with sequential indices to address that challenge. Specifically, a contour generation network is proposed based on Structural Low-Rank Descriptors for shape consistency, termed SLoRD. For a structural representation of vertebral contours, we adopt the spherical coordinate system and devise the spherical centroid to calculate contour descriptors. Due to vertebrae's similar appearances, basic contour descriptors can be acquired offline to restore original contours. Therefore, SLoRD leverages these contour priors and explicit shape constraints to facilitate regressed contour points close to vertebral surfaces. Quantitative and qualitative evaluations on VerSe 2019 and 2020 demonstrate the superior performance of our framework over other single-stage and multi-stage state-of-the-art (SOTA) methods. Further, SLoRD is a plug-and-play framework to refine the segmentation inconsistency existing in coarse predictions from other approaches. Source codes are available https://***/AlexYouXin/SLoRD-VerSe.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards unbiased random features with lower variance for stationary indefinite kernels

arXiv

引用

arXiv 2021年

作者： Luo, Qin Fang, Kun Yang, Jie Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

Random Fourier Features (RFF) demonstrate well-appreciated performance in kernel approximation for large-scale situations but restrict kernels to be stationary and positive definite. And for non-stationary kernels, the corresponding RFF could be converted to that for stationary indefinite kernels when the inputs are restricted to the unit sphere. Numerous methods provide accessible ways to approximate stationary but indefinite kernels. However, they are either biased or possess large variance. In this article, we propose the generalized orthogonal random features, an unbiased estimation with lower variance. Experimental results on various datasets and kernels verify that our algorithm achieves lower variance and approximation error compared with the existing kernel approximation methods. With better approximation to the originally selected kernels, improved classification accuracy and regression ability is obtained with our approximation algorithm in the framework of support vector machine and regression. © 2021, CC BY.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning

arXiv

引用

arXiv 2025年

作者： Huang, Zhehao Cheng, Xinwen Jie, Zhang Zheng, JingHao Wang, Haoran He, Zhengbao Li, Tao Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China

Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for data removal, forming the Continual Learning-Unlearning (CLU) paradigm. While existing work treats CL and MU as separate processes, we reveal their intrinsic connection through a unified optimization framework based on Kullback-Leibler divergence minimization. This framework decomposes gradient updates for approximate CLU into four components: learning new knowledge, unlearning targeted data, preserving existing knowledge, and modulation via weight saliency. A critical challenge lies in balancing knowledge update and retention during sequential learning-unlearning cycles. To resolve this stability-plasticity dilemma, we introduce a remain-preserved manifold constraint to induce a remaining Hessian compensation for CLU iterations. A fast-slow weight adaptation mechanism is designed to efficiently approximate the second-order optimization direction, combined with adaptive weighting coefficients and a balanced weight saliency mask, proposing a unified implementation framework for gradient-based CLU. Furthermore, we pioneer task-agnostic CLU scenarios that support fine-grained unlearning at the cross-task category and random sample levels beyond the traditional task-aware setups. Experiments demonstrate that the proposed UG-CLU framework effectively coordinates incremental learning, precise unlearning, and knowledge stability across multiple datasets and model architectures, providing a theoretical foundation and methodological support for dynamic, compliant intelligent systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

Evaluation of low-dose CT supervised learning algorithms with transformer-based model observer

arXiv

引用

arXiv 2022年

作者： Shi, Yongyi Wang, Ge Mou, Xuanqin Biomedical Imaging Center Rensselaer Polytechnic Institute TroyNY United States Institute of Image Processing and Pattern Recognition Xi’an Jiaotong University Shaanxi Xi’an China

A variety of supervise learning methods have been proposed for low-dose computed tomography (CT) sinogram domain denoising. Traditional measures of image quality have been employed to optimize and evaluate these methods, where mathematical model observers are widely advocated because it’s designed to act as human surrogates in the task of lesion detectability for clinical diagnosis. However, the sinogram domain evaluation for the supervised learning methods remains lacking. Since the lesion in medical images is correspond to a narrow sine strip in sinogram domain, in this paper, we proposed a transformer-based efficient model observer to evaluate the sinogram domain supervise learning methods. The numerical results indicate that, we can well-approximate the Laguerre-Gauss channelized Hotelling observer (LG-CHO) models for a signal-known-exactly (SKE) and background-known-statistically (BKS) task by training a transformer-based model observer in sinogram domain. The proposed transformer-based model observer is then employed to assess three classic CNN-based sinogram domain denoising methods. The evaluation in these denoising methods may suggest future avenues for improving the effectiveness of sinogram domain supervised learning methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

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：