检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jiao, Siyi Zeng, Wenzheng Li, Yerong Zhang, Huayu Gao, Changxin Sang, Nong Shou, Mike Zheng Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Show Lab National University of Singapore Singapore

Human instance matting aims to estimate an alpha matte for each human instance in an image, which is challenging as it easily fails in complex cases requiring disentangling mingled pixels belonging to multiple instances along hairy and thin boundary structures. In this work, we address this by introducing MP-Mat, a novel 3D-and-instance-aware matting framework with multiplane representation, where the multiplane concept is designed from two different perspectives: scene geometry level and instance level. Specifically, we first build feature-level multiplane representations to split the scene into multiple planes based on depth differences. This approach makes the scene representation 3D-aware, and can serve as an effective clue for splitting instances in different 3D positions, thereby improving interpretability and boundary handling ability especially in occlusion areas. Then, we introduce another multiplane representation that splits the scene in an instance-level perspective, and represents each instance with both matte and color. We also treat background as a special instance, which is often overlooked by existing methods. Such an instance-level representation facilitates both foreground and background content awareness, and is useful for other down-stream tasks like image editing. Once built, the representation can be reused to realize controllable instance-level image editing with high efficiency. Extensive experiments validate the clear advantage of MP-Mat in matting task. We also demonstrate its superiority in image editing tasks, an area under-explored by existing matting-focused methods, where our approach under zero-shot inference even outperforms trained specialized image editing techniques by large margins. Code is open-sourced at https://***/JiaoSiyi/***. 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

A membrane-inspired algorithm with a memory mechanism for knapsack problems

引用

Journal of Zhejiang University-Science C(Computers and Electronics) 2013年第8期14卷 612-622页

作者： Juan-juan HE Jian-hua XIAO Xiao-long SHI Tao SONG Key Laboratory of Image Processing and Intelligent Control School of AutomationHuazhong University of Science and Technology The Logistics Research Center Nankai University

Membrane algorithms are a class of distributed and parallel algorithms inspired by the structure and behavior of living cells. Many attractive features of living cells have already been abstracted as operators to improve the performance of algorithms. In this work, inspired by the function of biological neuron cells storing information, we consider a memory mechanism by introducing memory modules into a membrane algorithm. The framework of the algorithm consists of two kinds of modules (computation modules and memory modules), both of which are arranged in a ring neighborhood topology. They can store and process information, and exchange information with each other. We test our method on a knapsack problem to demonstrate its feasibility and effectiveness. During the process of approaching the optimum solution, feasible solutions are evolved by rewriting rules in each module, and the information transfers according to directions defined by communication rules. Simulation results showed that the performance of membrane algorithms with memory cells is superior to that of algorithms without memory cells for solving a knapsack problem. Furthermore, the memory mechanism can prevent premature convergence and increase the possibility of finding a global solution.

关键词： Membrane algorithm Memory mechanism Knapsack problem

来源：评论

学校读者我要写书评

暂无评论

Taming Consistency Distillation for Accelerated Human image Animation

arXiv

引用

arXiv 2025年

作者： Wang, Xiang Zhang, Shiwei Yuan, Hangjie Wei, Yujie Zhang, Yingya Gao, Changxin Wang, Yuehuan Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Fudan University China

Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs and slow speeds. An intuitive solution involves adopting consistency models, which serve as an effective acceleration paradigm through consistency distillation. However, simply employing this strategy in human image animation often leads to quality decline, including visual blurring, motion degradation, and facial distortion, particularly in dynamic regions. In this paper, we propose the DanceLCM approach complemented by several enhancements to improve visual quality and motion continuity at low-step regime: (1) segmented consistency distillation with an auxiliary light-weight head to incorporate supervision from real video latents, mitigating cumulative errors resulting from single full-trajectory generation;(2) a motion-focused loss to centre on motion regions, and explicit injection of facial fidelity features to improve face authenticity. Extensive qualitative and quantitative experiments demonstrate that DanceLCM achieves results comparable to state-of-the-art video diffusion models with a mere 2-4 inference steps, significantly reducing the inference burden without compromising video quality. The code and models will be made publicly available. 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

Modality Unified Attack for Omni-Modality Person Re-Identification

引用

IEEE Transactions on Information Forensics and Security 2025年

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omnimodality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. © 2005-2012 IEEE.

关键词： Modality unified attack Multi Modality Collaborative Disruption Omni-Modality re-id

来源：评论

学校读者我要写书评

暂无评论

A Game Theory-Reinforcement Learning Approach to Cooperation for UAVs

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Tang, Changbing Pan, Linchao Chen, Jie Liu, Yang Lai, Jingang The College of Physics and Electronic Information Engineering Zhejiang Normal University Jinhua321004 China The School of Mathematical Sciences Zhejiang Normal University Jinhua321004 China The Hangzhou School of Automation Zhejiang Normal University Hangzhou311231 China The College of Electronic Engineering National University of Defense Technology Hefei230037 China The School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control Education Ministry of China China Huazhong University of Science and Technology Wuhan430074 China

To execute a variety of collaborative tasks, the cooperation for unmanned aerial vehicles (UAVs) with complicated interactions under dynamic environments is a challenging and critical issue. This paper studies the cooperation issue for UAVs under dynamic environments through an approach of game theory-reinforcement learning (GT-RL) approach, which combines the advantages of both game theory and reinforcement learning. First, to cope with the complicated interactions of UAVs, the cluster of UAVs is modeled as a public goods game with asymmetrical environmental feedback. Then, reinforcement learning is adopted to optimize decision-making of UAVs under unknown and dynamic environments through comparing the dynamic behaviors of UAVs, where a novel dynamics system offers a more comprehensive understanding on cooperative behavior among UAVs. Finally, the simulation results show that the GT-RL approach can effectively promote cooperation among UAVs in completing the collaborative tasks. © 1967-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of Application-Layer Rateless Codes Based on Reliability and Latency Trade-Off

Analysis and Design of Application-Layer Rateless Codes Base...

引用

IEEE Conference on Wireless Communications and Networking

作者： Haobo Huang Yusun Fu Junpeng Yin Ningbo Artificial Intelligence Institute Shanghai Jiao Tong University Ningbo China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

With the Internet of Things (IoT) playing an increasingly crucial role in connecting diverse devices, applications have different requirements for communication and various evaluation metrics have emerged, such as Age of Information (AoI) and estimation error. Considering the fundamental trade-off between reliability and latency of the communication system, the relationship among reliability, latency, AoI and estimation error is complex. This paper proposes a remote state observation system with application-layer rateless codes to explore above relationships, addressing how to design the system for optimal performance based on varying requirements by adjusting coding parameters. By emphasizing flexible and adaptable coding strategies, we aim to convey the idea that the error-correction codes can be designed to optimize the communication system for diverse practical metrics. It is different from the traditional designs that focus on approaching the Shannon limit.

关键词： Measurement Estimation error Correlation Communication systems Reliability engineering Information age Error correction codes Internet of Things Channel coding State estimation

来源：评论

学校读者我要写书评

暂无评论

Research advances and prospect of spiking neural P systems

引用

Jisuanji Xuebao/Chinese Journal of Computers 2008年第12期31卷 2090-2096页

作者： Pan, Lin-Qiang Zhang, Xing-Yi Zeng, Xiang-Xiang Wang, Jun Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China

Spiking neural P systems are a new computing model inspired from the biological phenomena that in the brain the neurons cooperate to deal with spikes by axons. Since it has been shown that they have powerful computational capability and potential capability in solving computationally hard problems, more and more people begin to get interested in this field. This paper firstly introduces the formal definition of standard spiking neural P systems and some notions which are often used in this area;then, several extensions of the original spiking neural P systems are summarized, that are: Extented SN P system;SN P system with exhaustive use of rules;Asynchronous SN P system;Sequential SN P system. Also, the results on the topic of spiking neural P systems are briefly recalled in two aspects: computational completeness and computational efficiency. In the end, two more important future research directions on spiking neural P systems are pointed out. Specifically, one interesting topic is to develop a new computing model which is more "realistic";another topic is to consider how to use these models in biological modeling and simulation.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Recursive Least Squares Identification With Variable-Direction Forgetting via Oblique Projection Decomposition

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 547-555页

作者： Kun Zhu Chengpu Yu Yiming Wan Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology Beijing Institute of Technology Chongqing Innovation Center

In this paper,a new recursive least squares(RLS)identification algorithm with variable-direction forgetting(VDF)is proposed for multi-output *** objective is to enhance parameter estimation performance under non-persistent *** proposed algorithm performs oblique projection decomposition of the information matrix,such that forgetting is applied only to directions where new information is *** proofs show that even without persistent excitation,the information matrix remains lower and upper bounded,and the estimation error variance converges to be within a finite ***,detailed analysis is made to compare with a recently reported VDF algorithm that exploits eigenvalue decomposition(VDF-ED).It is revealed that under non-persistent excitation,part of the forgotten subspace in the VDF-ED algorithm could discount old information without receiving new data,which could produce a more ill-conditioned information matrix than our proposed *** simulation results demonstrate the efficacy and advantage of our proposed algorithm over this recent VDF-ED algorithm.

关键词： Non-persistent excitation oblique projection recursive least squares(RLS) variable-direction forgetting(VDF)

来源：评论

学校读者我要写书评

暂无评论

Analyzing Cognitive Patterns in Gifted Children Using MRI and Morphometric Similarity Networks

Analyzing Cognitive Patterns in Gifted Children Using MRI an...

引用

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Han, Shuning Duan, Feng Vilaseca, Gemma Vilaró, Núria Caiafa, Cesar F. Sun, Zhe Solé-Casals, Jordi Data and Signal Processing Research Group University of Vic-Central University of Catalonia Vic Catalonia Spain Image Processing Research Group RIKEN Center for Advanced Photonics RIKEN Saitama Wako-Shi Japan Tianjin Key Laboratory of Brain Science and Intelligent Rehabilitation Nankai University Tianjin China Psychological Department Oms and Prat school Fundació Catalunya- La Pedrera Catalonia Manresa Spain Oms Foundation Catalonia Manresa Spain Instituto Argentino de Radioastronomıa-CCT La Plata CONICET / CIC-PBA / UNLP Argentina Faculty of Health Data Science Juntendo University Chiba Urayasu Japan Department of Psychiatry University of Cambridge Cambridge United Kingdom

Advances in non-invasive neuroimaging, such as structural magnetic resonance imaging (sMRI), have en abled the construction of structural brain networks (SBNs), allowing in vivo mapping of anatomical connec tions. This study investigates brain network structural differences linked to different intelligence levels in children by individual morphometric similarity networks (MSNs) derived from sMRI data. Through group and individual-level analyses, we aim to uncover key topological features associated with cognitive perfor mance and to identify a suitable connection density for SBN analysis. Connection density strongly affects global and nodal topological features, with a range of p = 0.05 to 0.15 recommended for stable and optimal results. Gifted individuals exhibit stronger intra-hemispheric and intra-modular connectivity, a more balanced distribution of left-to-right intra-hemispheric connections, and lower mean versatility, supporting efficient and stable cognitive processing. Moreover, anatomical modularity analyses based on von Economo indicate that higher cognitive performance is linked to enhanced connectivity in specific areas (such as secondary sensory area, motor to association area and secondary sensory to limbic area), alongside selective reduction in cer tain modular connections (such as motor to insular area, association to secondary sensory area and motor to secondary sensory area). Furthermore, topological features, including participation coefficient and local effi ciency, are linked to cognitive performance. These findings provide valuable insights into the SBNs underlying cognitive levels in children. © 2025 by SCITEPRESS– Science and Technology Publications, Lda.

关键词： Brain mapping

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：