检索结果-内蒙古大学图书馆

Tracking Like Human: Dynamic Scene Learning Reasoning Tracker in Satellite Videos

IEEE Transactions on Multimedia 2025年

作者： Yang, Xiaoyan Jiao, Licheng Li, Yangyang Liu, Xu Li, Lingling Chen, Puhua Liu, Fang Ma, Wenping Yang, Shuyuan Xidian University Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China International Research Center of Intelligent Perception and Computation School of Artificial Intelligence Xi'an China Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi'an 710049 China

In satellite video object tracking, the individual frame analysis method is usually used for target localization, ignoring informative cues of the dynamic scene. Temporal information could contribute to identifying the target from distractors. In this work, a novel dynamic scene learning reasoning tracker is proposed for satellite videos, which reasons over temporal dynamic information to derive the target location. It is inspired by the tracking pattern through human perception and reasoning. First, static-dynamic united analysis is designed to construct dynamic scenes by concatenating the static searching results along the temporal dimension. Second, the information of each response object is aggregated by wavelet transforms. Meanwhile, these scenes are projected into low-frequency and high-frequency subspaces, which could imitate different levels of perceptions of humans for scenes. Third, an object-aware reasoning transformer is proposed to utilize the temporal dynamics of input response objects. In each subspace, it models the mutual interactions between dynamic objects and further learns the intrinsic property of each object for target reasoning. Finally, to obtain the current reasoning result, inverse wavelet transforms are utilized to integrate the results of low-frequency and high-frequency subspaces. The effectiveness of the proposed method is validated on three public satellite video datasets, including SV248S, SkySat, and VISO. Qualitative and quantitative experimental results show that the proposed tracker outperforms 22 popular approaches in seven challenging tracking satellite scenarios. © 1999-2012 IEEE.

关键词： object tracking relation reasoning Satellite videos

来源：评论

学校读者我要写书评

暂无评论

LATEXBLEND: Scaling Multi-concept Customized Generation with Latent Textual Blending

arXiv

引用

arXiv 2025年

作者： Jin, Jian Yu, Zhenbo Shen, Yang Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. China

Customized text-to-image generation renders user-specified concepts into novel contexts based on textual prompts. Scaling the number of concepts in customized generation meets a broader demand for user creation, whereas existing methods face challenges with generation quality and computational efficiency. In this paper, we propose LATEXBLEND, a novel framework for effectively and efficiently scaling multi-concept customized generation. The core idea of LATEXBLEND is to represent single concepts and blend multiple concepts within a Latent Textual space, which is positioned after the text encoder and a linear projection. LATEXBLEND customizes each concept individually, storing them in a concept bank with a compact representation of latent textual features that captures sufficient concept information to ensure high fidelity. At inference, concepts from the bank can be freely and seamlessly combined in the latent textual space, offering two key merits for multi-concept generation: 1) excellent scalability, and 2) significant reduction of denoising deviation, preserving coherent layouts. Extensive experiments demonstrate that LATEXBLEND can flexibly integrate multiple customized concepts with harmonious structures and high subject fidelity, substantially outperforming baselines in both generation quality and computational efficiency. Project Page. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptation and learning of spatio-temporal thresholds in spiking neural networks

引用

Neurocomputing 2025年 644卷

作者： Fu, Jiahui Gou, Shuiping Wang, Peizhao Jiao, Licheng Guo, Zhang Li, Jisheng Liu, Rong Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Shannxi Xi'an 710071 China School of Physics and Information Technology Shaanxi Normal University Shannxi Xi'an 710119 China

Spiking neural networks (SNNs) have attracted substantial attention in recent years due to their brain-inspired and event-driven characteristics. To mimic the behavior of biological neurons, the neuron in SNNs generates spikes to transmit information across the network once its membrane potential surpasses a certain firing threshold. Due to model complexity and computational challenges, the threshold is often set as a fixed value, which limits the rich dynamical features of neurons and is inconsistent with the dynamic nature of thresholds observed in biological systems. Additionally, treating the threshold as an optimized parameter presents challenges in achieving convergence and maintaining stability. Therefore, we introduce a spatio-temporal adjustment strategy for the firing threshold. We propose a Learnable Temporal Factor (LTF) to dynamically adapt the threshold over time and an Adaptive Learnable Spatial Factor (ALSF) to spatially extend the threshold. By coupling these factors with the neuronal dynamics, we achieve a stronger spike coding capacity by utilizing more information in the generation of spikes. Our experiments show that the proposed method yields remarkable performance on both static and neuromorphic datasets. Our code is available at ***/gzxdu/ST-Thresholds-SNN. © 2025

关键词： Dynamic vision sensor Spatio-temporal thresholds Spike coding capacity Spiking neural networks

来源：评论

学校读者我要写书评

暂无评论

DBA-RMCL: Refined Metric Contrastive Learning With Dual-Branch Attention for Few-Shot Remote Sensing image Scene Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Dong, Ruchan Xia, Jinwei Jiao, Licheng Hong, Lei Yun, Zengxin Jinling Institute of Technology Nanjing211169 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education School of Artificial Intelligence China Xi’an Jiaotong University School of Mathematics and Statistics Xi’an710049 China

Remote sensing scene classification plays a vital role in identifying Earth’s surface features. However, traditional methods necessitate vast quantities of labeled training data, which significantly limits their applicability when labeled samples are scarce. To overcome this limitation, remote sensing few-shot classification (RSFSC) methods have arisen as a promising approach to maintaining classification accuracy with minimal data. In this article, we present a refined metric contrastive learning framework with dual-branch attention (DBA-RMCL), a novel framework that tackles two fundamental challenges in RSFSC: intraclass diversity and interclass similarity. Our framework employs a dual-branch architecture consisting of way and shot branches to reduce intraclass variance while enhancing feature consistency and interclass separability. The architecture incorporates feature fusion between branches to optimize feature learning and classification performance. We further enhance feature representations through our refined Siamese contrastive learning representation (RSCLR) module, which implements self-supervised contrastive learning. The framework also includes a combined attention-based prototypical head (CAP-Head) module with a compositional attention computation unit to model complex relationships between query sets and prototypes. Experimental results on six publicly available datasets demonstrate that DBA-RMCL achieves state-of-the-art performance compared to existing FSC methods. For 5-way 1-shot tasks, our framework attains accuracies of 77.15% ± 0.34 % on NWPU-RESISC45 and 87.33% ± 0.22 % on WHU-RS19. Additionally, we established the first benchmark for few-shot scene classification, MEET-FSL, using the MEET dataset. These outcomes not only underscore the efficacy of our dual-branch architecture but also represent a significant advancement in the field of few-shot learning for remote sensing classification. © 1980-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

ViewCAM: A Weakly Supervised Building Extraction Method Based on View Consistency and Feature Affinity Enhancement

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Bai, Jing Gu, Mansu Chen, Zheng Li, Tong Xiao, Zhu Li, Ping Jiao, Licheng Xidian University School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xi'an710071 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Shenzhen Research Institute Hunan University Shenzhen518055 China Chongqing Changxian Intelligent Technology Company Ltd. Chongqing510062 China

In building extraction, collecting pixel-level annotations required by fully supervised methods is extremely costly. image-level weakly supervised methods based on class activation maps (CAMs) effectively reduce the cost and have shown promising progress. However, generating high-quality CAMs remains challenging due to the supervision gap between classification and segmentation tasks. Specifically, image-level supervision causes CAMs to activate only the most discriminative regions, which compromises the integrity of CAMs. Meanwhile, the absence of pixel-level supervision leads to a depletion of spatial information, resulting in imprecise boundaries. In this study, we propose a novel image-level weakly supervised building extraction method based on view consistency, named ViewCAM, to generate high-quality CAMs. The view transformation module (VTM) is designed to apply view transformations to remote sensing images and high-dimensional features. In addition, a feature affinity enhancement module (FAEM) is proposed to capture positional relationships between pixels and low-level features, such as edges and textures, improving boundary fineness. We integrate these two modules into a classification network and incorporate pixel-level supervision using view-consistency constraints. The entire network is then trained in an end-to-end manner, leading to improved integrity and boundary fineness of the seeds generated from CAMs. To verify the effectiveness and robustness of ViewCAM, we conduct experiments on two representative datasets, and the results demonstrate that our proposed method achieves superior CAM integrity and boundary fineness, outperforming state-of-the-art methods. © 1980-2012 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Adaptive Homophily Clustering: Structure Homophily Graph Learning with Adaptive Filter for Hyperspectral image

arXiv

引用

arXiv 2025年

作者： Ding, Yao Kang, Weijie Yang, Aitao Zhang, Zhili Zhao, Junyang Feng, Jie Hong, Danfeng Zheng, Qinghe The Key Laboratory of Intelligent Control PLA Rocket Force University of Engineering Xi’an710025 China The Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University Xi’an710071 China The Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China The School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Hyperspectral image (HSI) clustering has been a fundamental but challenging task with zero training labels. Currently, some deep graph clustering methods have been successfully explored for HSI due to their outstanding performance in effective spatial structural information encoding. Nevertheless, insufficient structural information utilization, poor feature presentation ability, and weak graph update capability limit their performance. Thus, in this paper, a homophily structure graph learning with an adaptive filter clustering method (AHSGC) for HSI is proposed. Specifically, homogeneous region generation is first developed for HSI processing and constructing the original graph. Afterward, an adaptive filter graph encoder is designed to adaptively capture the high and low frequency features on the graph for subsequence processing. Then, a graph embedding clustering self-training decoder is developed with KL Divergence, with which the pseudo-label is generated for network training. Meanwhile, homophily-enhanced structure learning is introduced to update the graph according to the clustering task, in which the orient correlation estimation is adopted to estimate the node connection, and graph edge sparsification is designed to adjust the edges in the graph dynamically. Finally, a joint network optimization is introduced to achieve network self-training and update the graph. The K-means is adopted to express the latent features. Extensive experiments and repeated comparative analysis have verified that our AHSGC contains high clustering accuracy, low computational complexity, and strong robustness. The code source will be available at https://***/DY-HYX. Copyright © 2025, The Authors. All rights reserved.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Triple Point Masking

引用

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

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：