检索结果-内蒙古大学图书馆

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Liu, Jiaming Kong, Linghe Wu, Yue Gong, Maoguo Li, Hao Miao, Qiguang Ma, Wenping Qin, Can The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Technology Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The College of Mathematics Science Inner Mongolia Normal University Hohhot010022 China The School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi’an710071 China The Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable plug- and-play framework for MAE pre-training to achieve multi-mask learning for 3D point clouds. Specifically, we augment the baseline methods with two additional mask choices (i.e., medium mask and low mask) as our core insight is that the recovery process of an object can manifest in diverse ways. Previous high-masking schemes focus on capturing the global representation information but lack fine-grained recovery capabilities, so that the generated pre-training weights tend to play a limited role in the fine-tuning process. With the support of the proposed TPM, current methods can exhibit more flexible and accurate completion capabilities, enabling the potential autoencoder in the pre-training stage to consider multiple representations of a single 3D point cloud object. In addition, during the fine-tuning stage, an SVM-guided weight selection module is proposed to fill the encoder parameters for downstream networks with the optimal weight, maximizing linear accuracy and facilitating the acquisition of intricate representations for new objects. Extensive experimental results and theoretical analysis show that five baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks. © 2025 IEEE. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

A comparative study of network robustness measures

引用

Frontiers of Computer Science 2017年第4期11卷 568-584页

作者： Jing LIU Mingxing ZHOU Shuai WANG Penghui LIU Key Laboratory of intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an 710071 China

The robustness is an important functionality of networks because it manifests the ability of networks to resist failures or attacks. Many robustness measures have been proposed from different aspects, which provide us various ways to evaluate the network robustness. However, whether these measures can properly evaluate the network robustness and which aspects of network robustness these measures can evaluate are still open questions. Therefore, in this paper, a thorough introduction over attacks and robustness measures is first given, and then nine widely used robustness mea- sures are comparatively studied. To validate whether a robustness measure can evaluate the network robustness properly, the sensitivity of robustness measures is first studied on both initial and optimized networks. Then, the performance of robustness measures in guiding the optimization process is studied, where both the optimization process and the ob- tained optimized networks are studied. The experimental re- suits show that, first, the robustness measures are more sen- sitive to the changes in initial networks than to those in op- timized networks; second, an optimized network may not be useful in practical situations because some useful function- alities, such as the shortest path length and communication efficiency, are sacrificed too much to improve the robustness; third, the robustness of networks in terms of closely corre- lated robustness measures can often be improved together. These results indicate that it is not wise to just apply the opti- mized networks obtained by optimizing over one certain robustness measure into practical situations. Practical requirements should be considered, and optimizing over two or more suitable robustness measures simultaneously is also a promising way.

关键词： scale-free network malicious attack robustnessmeasure hill climbing algorithm

来源：评论

学校读者我要写书评

暂无评论

Mathematical model and simulated annealing algorithm for Chinese high school timetabling problems under the new curriculum innovation

引用

Frontiers of Computer Science 2021年第1期15卷 167-177页

作者： Xingxing HAO Jing LIU Yutong ZHANG Gustaph SANGA Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian UniversityXi’an 710071China

As the first attempt,this paper proposes a model for the Chinese high school timetabling problems(CHSTPs)under the new curriculum innovation which was launched in 2011 by the Chine6e *** 10 the new our riculum innovation,students in high school can choose subjects that they are interested in instead of being forced to select one of the two study directions,namely,Science and Liberal ***,they also need to attend compulsory subjects as *** are student-oriented and involve more student constraints that make them more complex than the typi-cal"Class-Teacher model",in which the element"Teacher"is the primary *** this paper,we first describe in detail the mathematical model of CHSTPs and then design a new two-part representation for the candidate *** on the new representation,we adopt a two-phase simulated annealing(SA)algorithm to solve CHSTPs.A total number of 45 synthetic instances with different amounts of classes,teachers,and levels of student constraints are generated and used to ilustrate the characteristics of the CHSTP model and the effectiveness of the designed representation and ***,we apply the proposed model,the designed two-part representation and the two-phase SA on10 real high schools.

关键词： timetabling Chinese high school timetabling problem simulated annealing two-part representation

来源：评论

学校读者我要写书评

暂无评论

Optimization methods for regularization-based ill-posed problems： a survey and a multi-objective framework

引用

Frontiers of Computer Science 2017年第3期11卷 362-391页

作者： Maoguo GONG Xiangming JIANG Hao LI Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an 710071 China

Ill-posed problems are widely existed in signat processing. In this paper, we review popular regularization models such as truncated singular value decomposi- tion regularization, iterative regularization, variational regularizafion. Meanwhile, we also retrospect popular optimiza- tion approaches and regularization parameter choice meth- ods. In fact, the regularization problem is inherently a multi- objective problem. The traditional methods usually combine the fidelity term and the regularization term into a single- objective with regularization parameters, which are difficult to tune. Therefore, we propose a multi-objective framework for ill-posed problems, which can handle complex features of problem such as non-convexity, discontinuity. In this framework, the fidelity term and regularization term are optimized simultaneously to gain more insights into the ill-posed prob- lems. A case study on signal recovery shows the effectiveness of the multi-objective framework for ill-posed problems.

关键词： ill-posed problem regularization multi- objective optimization evolutionary algorithm signal processing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Student Behavior Analysis via YOLOv5 with Coordinate Attention 9th

Real-Time Student Behavior Analysis via YOLOv5 with Coordina...

引用

9th International Symposium on Artificial Intelligence and Robotics, ISAIR 2024

作者： Ma, Shuai Chang, Heyou Yang, Xinru Chen, Quan Han, Jian Key Laboratory of Intelligent Information Processing Nanjing XiaoZhuang University Nanjing China School of Information and Engineering Nanjing XiaoZhuang University Nanjing China School of Computer Science Nanjing University of Information Science and Technology Nanjing China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9789819629138

The detection and recognition of student behavior play a pivotal role in the context of smart classrooms. However, conventional methods often encounter performance degradation due to challenges such as occlusion, data diversity, and complexity. To effectively addresses these issues, we propose a method that integrates YOLOv5 with coordinate attention mechanism and GhostConv for analyzing students' behavior. Specifically, the coordinate attention module enhances the localization ability of the proposed method by addressing problems related to target scale variations and uneven distribution. Additionally, we employ GhostConv to replace conventional convolutional layers in YOLOv5, reducing parameters while improving computational efficiency. To verify the validity of our method, a self-built challenging dataset for real teaching scenarios and Citypersons dataset are selected for the experiment. In comparison to the original YOLOv5, our method has achieved a 14.8% and 5.7% increase in mean average precision rates, with a 19.0% improvement in frames per second. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Asymptotics-Aware Multi-View Subspace Clustering

引用

IEEE Transactions on Multimedia 2025年

作者： Xu, Yesong Chen, Shuo Li, Jun Yang, Jian Anhui Polytechnic University School of Computer and Information Wuhu241000 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Nanjing University of Science and Technology PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

Recently, multi-view subspace clustering has attracted extensive attention due to the rapid increase of multi-view data in many real-world applications. The main goal of this task is to learn a common representation of multiple subspaces from the given multi-view data, and most existing methods usually directly merge multiple groups of features by the single-step integration. However, there may exist large disparities among different views of the data, and thus the conventional single-step practice can hardly obtain a generally consistent feature representation for the multi-view data. To overcome this challenge, we present a novel approach dubbed "Asymptotics-Aware Multi-view Subspace Clustering (A2 MSC)"to pursue a consistent feature representation in a multi-step way, which iteratively conducts the data recovery to gradually reduce the differences between pairwise views. Specifically, we construct an asymptotic learning rule to update the feature representation, and the iteration result converges to a consistent feature vector for characterizing each instance of the original multi-view data. After that, we utilize such a new feature representation to learn a clustering-oriented similarity matrix via minimizing a self-expressive objective, and we also design the corresponding optimization algorithm to solve it with convergence guarantees. Theoretically, we prove that the learned asymptotic representation effectively integrates multiple views, thereby ensuring the effective handling of multi-view data. Empirically, extensive experimental results demonstrate the superiority of our proposed A2 MSC over the state-of-the-art multi-view subspace clustering approaches. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Dense-Weak Ship Detection based on Foreground-Guided Background Generation Network in SAR images

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Ma, Wenping Yang, Xiaoting Zhu, Hao Wang, Xiaoteng Hou, Biao Ma, Mengru Wu, Yue Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Shaanxi Province Xi’an710126 China

Currently, ship detection based on Synthetic Aperture Radar (SAR) images still faces significant challenges, particularly in detecting weak and densely distributed ships within complex backgrounds. In areas such as ports and land, the complex background features often resemble those of densely distributed ships, leading to reduced detection accuracy. Additionally, the overlapping and mutual interference of features among dense ships can cause the network to miss detections or produce false positives. Therefore, this paper proposes a Foreground-Guided Background Generation Network (FGBG-Net), which includes a Gaussian Foreground Localization (GFL) model and a Background Feature Removal (BFR) module. The GFL module identifies the approximate high-probability regions of ship foregrounds on the feature map, guiding the network to focus on these regions. The BFR module then progressively removes background interference features based on the positions provided by the GFL module, generating feature maps that are more suitable for detecting weak and dense ships. Our network has been validated on multiple SAR ship datasets, and the experimental results demonstrate noticeable performance improvements, with a mean Average Precision (mAP) increase of 3.4% on the SSDD and HRSID datasets. © 1980-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Reference direction based immune clone algorithm for many-objective optimization

引用

Frontiers of Computer Science 2014年第4期8卷 642-655页

作者： Ruochen LIU Chenlin MA Fei HE Wenping MA Licheng JIAO Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Xidian University Xi'an 710071 China

In this paper, a new preference multi-objective optimization algorithm called immune clone algorithm based on reference direction method （RD-ICA） is proposed for solving many-objective optimization problems. First, an intelligent recombination operator, which performs well on the functions comprising many parameters, is introduced into an immune clone algorithm so as to explore the potentially excellent gene segments of all individuals in the antibody pop- ulation. Second, a reference direction method, a very strict ranking based on the desire of decision makers （DMs）, is used to guide selection and clone of the active population. Then a light beam search （LBS） is borrowed to pick out a small set of individuals filling the external population. The proposed method has been extensively compared with other recently proposed evolutionary multi-objective optimization （EMO） approaches over DTLZ problems with from 4 to 100 objectives. Experimental results indicate RD-ICA can achieve competitive results.

关键词： many-objective optimization preference multiobjective optimization artificial immune system reference direction method light beam search intelligent recombination operator

来源：评论

学校读者我要写书评

暂无评论

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label image Classification

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Jiangsu Nanjing210094 China JD Explore Academy Beijing100000 China Anhui University School of Computer Science and Technology Anhui Heifei230601 China Yunnan University FIST LAB School of Information Science and Engineering Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this article, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice"in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also provide a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the potential of extending our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. © 1999-2012 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Quantum Immune Clonal Selection Algorithm for Multi-objective 0/1 Knapsack Problems

引用

Chinese Physics Letters 2010年第1期27卷 37-40页

作者：尚荣华焦李成李阳阳吴建设 Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Institute of Intelligent Information Processing Xidian University Xi'an 710071

Based on the concept and principles of quantum computing and the principle of the immune clonal selection, a new algorithm for multi-objective 0/1 knapsack problems is introduced. In the algorithm, for the novel representation, qubit antibodies in the antibody population are updated by applying a new chaos update strategy. A quantitative metric is used for testing the convergence to the Pareto-optimal front. Simulation results on the 0/1 knapsack problems show that the new algorithm, in most cases, is more effective.

关键词： Chinese climate network complex systems small world community

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：