检索结果-内蒙古大学图书馆

Multi-scale Dilated Attention-based Generative Adversarial Network for Infrared and Visible Image Fusion

Current Optics and Photonics 2025年第2期9卷 120-129页

作者： Yang, Shunyuan Shi, Xiaoping Huo, Ju Sun, Kangjian Wang, Yu School of Astronautics Harbin Institute of Technology Harbin150001 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin150001 China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin150001 China Shanghai Space Propulsion Technology Research Institute Shanghai201109 China

In the field of optics, infrared and visible images are often required for use in different situations. In particular, in the field of optical sensors, infrared and visible sensors are mainly used to obtain different band images, which are applied to improve the comprehensive information content of images and to improve the quality and availability of images. In existing infrared and visible image fusion methods, the focus is often placed on retaining the background information from visible images and the salient targets from infrared images. To address this issue, we introduce a multi-scale dilated attention module into the encoder-decoder structure of the generator. By applying dilated convolution and selfattention mechanisms, this module improves the perceptual capability of the model, thereby improving performance without increasing network complexity. This design emphasizes gradient information and detailed features in visible images. Experimental results on the public TNO dataset demonstrate that our method achieves superior visual quality and preserves the most abundant image information. Moreover, experiments on spacecraft images validate the robustness and applicability of our approach. Simultaneously, our method also provides significant technical support for the optical field. © 2025 Current Optics and Photonics.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Imp: Highly Capable Large Multimodal Models for Mobile Devices

引用

IEEE Transactions on Multimedia 2025年

作者： Shao, Zhenwei Yu, Zhou Yu, Jun Ouyang, Xuecheng Zheng, Lihao Gai, Zhenbiao Wang, Mingyang Kuang, Zhenzhong Ding, Jiajun Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science Hangzhou310005 China Harbin Institute of Technology Shenzhen Department of Computer Science and Technology Shenzhen China Hangzhou Dianzi University HDU-ITMO Joint Institute Hangzhou310005 China

By harnessing the capabilities of large language models (LLMs), recent large multimodal models (LMMs) have shown remarkable versatility in open-world multimodal understanding. Nevertheless, they are usually parameter-heavy and computation-intensive, thus hindering their applicability in resource-constrained scenarios. To this end, several lightweight LMMs have been proposed successively to maximize the capabilities under constrained scale (e.g., 3B). Despite the encouraging results achieved by these methods, most of them only focus on one or two aspects of the design space, and the key design choices that influence model capability have not yet been thoroughly investigated. In this paper, we conduct a systematic study for lightweight LMMs from the aspects of model architecture, training strategy, and training data. Based on our findings, we obtain Imp - a family of highly capable LMMs at the 2B$\sim$4B scales. Notably, our Imp-3B model steadily outperforms all the existing lightweight LMMs of similar size, and even surpasses the state-of-the-art LMMs at the 13B scale. With low-bit quantization and resolution reduction techniques, our Imp model can be deployed on a Qualcomm Snapdragon 8Gen3 mobile chip with a high inference speed of about 13 tokens/s. © 2025 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Some new Liouville type theorems for 3D steady tropical climate model

arXiv

引用

arXiv 2025年

作者： Fang, Yan Zhang, Zhibing School of Mathematics and Physics Anqing Normal University Anqing246133 China School of Mathematics and Physics Key Laboratory of Modeling Simulation and Control of Complex Ecosystem in Dabie Mountains of Anhui Higher Education Institutes Anqing Normal University Anqing246133 China

In this paper, we study the Liouville type theorems for the stationary tropical climate model in three dimension. With the help of the delicate estimates of several integrals and an iteration argument, we establish Liouville type theorems under seventeen different assumptions. As a consequence, we show that a smooth solution is trivial provided that they belong to some Lebesgue spaces or satisfy some decay conditions at infinity. Our results extend and improve the recent work of Cho-In-Yang (2024 Appl. Math. Lett. 153 109039).MSC Codes 35B53, 35Q35, 35A02 © 2025, CC BY.

关键词： Climate models

来源：评论

学校读者我要写书评

暂无评论

Enhancing realism in LiDAR scene generation with CSPA-DFN and linear cross-attention via Diffusion Transformer model

引用

Neural Networks 2025年 189卷 107503页

作者： Ye, Shaoxun Di, Xiaoguang Liao, Ming Li, Ximing Control and Simulation Center Harbin Institute of Technology Harbin150080 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin150080 China

Point cloud diffusion models have found extensive applications in autonomous driving and robotics. However, there is still a big gap between their generated LiDAR scene samples and real-world data in terms of visual quality. This discrepancy primarily arises from the loss of detailed information during the decoding process from latent space and the lack of guidance from global 3D structural information in the point cloud generation process, leading to distortions and artifacts in LiDAR scene samples. In this paper, we propose a novel LiDAR Diffusion Transformer Model that integrates Channel-Spatial Parallel Attention and Dilation Fusion Network (CSPA-DFN) with a linear cross-attention post-processing module to refine the generated LiDAR scene samples. Specifically, CSPA-DFN is designed to simultaneously emphasize detailed features across different channels and spatial locations in parallel, leveraging multi-scale dilated convolutions and channel grouping to preserve and enhance these detailed features. In order to provide global 3D structural information and balance performance and efficiency, we design a post-processing module that fuses voxelized features and range images using a linear ReLU cross-attention mechanism. Our approach is evaluated on the unconditional generation task using the KITTI-360 and nuScenes datasets, achieving the state-of-the-art results in LiDAR scene's generation quality. Furthermore, by incorporating semantic labels and camera views into the latent space, in addition to enhancing the model's semantic understanding capability for LiDAR scenes, our method also demonstrates additional performance improvements compared to previous works in terms of LiDAR scene's visual quality. The code implementation has been released on https://***/HITysx/LiDAR-Scene-Generation. © 2025 Elsevier Ltd

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年

作者： Yu, Zhou Ouyang, Xuecheng Shao, Zhenwei Wang, Meng Yu, Jun Hangzhou Dianzi University School of Computer Science Key Laboratory of Complex Systems Modeling and Simulation China Hangzhou Dianzi University HDU-ITMO Joint Institute China Hefei University of Technology School of Computer Science and Information Engineering China Department of Computer Science and Technology Harbin Institute of Technology Shenzhen China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of the blind LLM as the provided textual input is insufficient to depict the required visual information to answer the question. In this paper, we present Prophet—a conceptually simple, flexible, and general framework designed to prompt LLM with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the VQA model: answer candidates and answer-aware examples. The two types of answer heuristics are jointly encoded into a formatted prompt to facilitate the LLM's understanding of both the image and question, thus generating a more accurate answer. By incorporating the state-of-the-art LLM GPT-3 [1], Prophet significantly outperforms existing state-of-the-art methods on four challenging knowledge-based VQA datasets. Prophet is general that can be instantiated with the combinations of different VQA models (i.e., both discriminative and generative ones) and different LLMs (i.e., both commercial and open-source ones). Moreover, Prophet can also be integrated with modern large multimodal models in different stages, which is named Prophet++, to further improve the capabilities on knowledge-based VQA tasks. © 1979-2012 IEEE.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Evolutionary neural architecture search for automatically designing CNN-GRU-Attention neural networks for turntable servo systems

引用

Expert Systems with Applications 2025年 283卷

作者： Xie, Cheng Xue, Bing Yang, Mingyi Zhang, Mengjie Xu, Zhigang Wang, Junyi Chen, Songlin Liu, Yang Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang110169 China Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand University of Chinese Academy of Sciences Beijing101408 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology Heilongjiang Harbin150001 China

Turntable servo systems are important experimental devices utilized in the semi-physical simulation and testing of aircraft. Building a model for turntable servo systems, which can accurately predict their operating states or behaviors, is important for the development and debugging of the whole servo control system. However, servo systems usually have complex nonlinear characteristics and external disturbances, which brings challenges to the accurate modeling of them. Therefore, this paper develops a modeling method for turntable servo systems by using CNN-GRU-Attention hybrid neural network models. The CNN-GRU-Attention model is used for compensating the nonlinear terms of the known dynamics model, thus effectively improving the modeling accuracy. Considering the complex architectures of the above hybrid model, an evolutionary neural architecture search (ENAS) algorithm is proposed accordingly, which can automatically design the architecture of the CNN-GRU-Attention models. During the designing process, a variable-length encoding strategy is proposed to represent the possible architectures, and novel crossover and mutation operators are proposed accordingly for the evolution of individuals. In addition, the real-time constraints are considered in the design of the search space, so that all the searched models can meet the real-time requirements. The experimental results show the CNN-GRU-Attention models obtained by the proposed ENAS algorithm achieve superior prediction performance over the peer competitors in most tasks. The effectiveness of the proposed method is further verified by analyzing the convergence and the search results. © 2025

关键词： Synchros

来源：评论

学校读者我要写书评

暂无评论

A constructive method for approximating trigonometric functions and their integrals

引用

Applied Mathematics(A Journal of Chinese Universities) 2020年第3期35卷 293-307页

作者： CHEN Xiao-diao WANG Long-quan WANG Yi-gang Key Laboratory of Complex Systems Modeling and Simulation Hangzhou Dianzi UniversityHangzhou 310027China

This paper presents an interpolation-based method(IBM)for approximating some trigonometric functions or their integrals as *** provides two-sided bounds for each function,which also achieves much better approximation effects than those of prevailing *** principle,the IBM can be applied for bounding more bounded smooth functions and their integrals as well,and its applications include approximating the integral of sin(x)/x function and improving the famous square root inequalities.

关键词： Padéapproximant trigonometric function constructive method interpolation-based method two-sided bounds

来源：评论

学校读者我要写书评

暂无评论

Dynamic analysis of rigid-flexible coupling spacecraft based on Euler parameters

引用

Scientific Reports 2025年第1期15卷 1-12页

作者： Ji, Yi Zhang, Huan School of Astronautics Harbin Institute of Technology Harbin 150001 China Frontier Science Center for Interaction between Space Environment and Matter Harbin 150001 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin 150001 China MOE Key Laboratory of Dynamics and Control of Flight Vehicle Beijing Institute of Technology Beijing 100081 China

With the development of aerospace technology, rigid-flexible coupling spacecraft with strong nonlinearity dominates, bringing huge challenges for numerical tools. This paper aims to accurately and quickly analyze the dynamic behavior of rigid-flexible coupling spacecraft. In our work, rigid body and flexible body are both described by Euler parameters for avoiding singular angles. Then, for this type of strong nonlinear dynamic system, the BN-stable method that is unconditionally stable for nonlinear initial value problems proposed by the first author is introduced to solve the transient responses. To keep the accuracy of the numerical rotation matrix, the relation between the angular velocity and Euler parameters, and the constraint in the level of velocity, are introduced to reformulate the original BN-stable method. Through the dynamic analysis for rigid satellite bodies and flexible solar wings, we find that the proposed strategy can effectively simulate the dynamic responses of spacecraft, and compared to the currently popular strategy, our strategy enjoys considerable advantages in accuracy, stability, and dissipation. © The Author(s) 2025.

关键词： BN-stability Dynamic analysis Euler parameters Rigid-flexible coupling Rotation matrix

来源：评论

学校读者我要写书评

暂无评论

A new general formulation of a transfer-function matrices of 2D digital systems

引用

Australian Journal of Electrical and Electronics Engineering 2019年第2期16卷 81-85页

作者： Bouhamla, Lakhdar Adamou-Mitiche, Amel Baha Houda Mitiche, Lahcène Laboratory of Research Modeling Simulation and Optimization of Real Complex Systems University Ziane Achour Djelfa Algeria

The contribution of our paper is a new simple method for transfer-function matrices derivation in two-dimensional digital systems from Roesser’s model is given. The main idea of this method is changing the form of the transfer-function, from state space to a fraction with a polynomial numerator and denominator. Then by identity, we can derive matrices of numerator and denominator. Numerical examples are given to prove the effectiveness and the simplicity of the proposed method. © 2019, © 2019 Engineers Australia.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

A PARALLEL DOMAIN DECOMPOSITION METHOD FOR SOLVING ELLIPTIC EQUATIONS ON MANIFOLDS

引用

SIAM Journal on Scientific Computing 2025年第2期47卷 A916-A942页

作者： Qin, Lizhen Wang, Feng Wang, Yun School of Mathematics Nanjing University Nanjing210093 China Key Laboratory of Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Ministry of Education Nanjing210023 China Jiangsu International Joint Laboratory of Big Data Modeling Computing and Application Nanjing Normal University Nanjing210023 China School of Mathematical Sciences Nanjing Normal University Nanjing210023 China School of Mathematical Sciences Center for Dynamical Systems and Differential Equations Soochow University Suzhou215006 China

We propose a new numerical domain decomposition method for solving elliptic equations on compact Riemannian manifolds. One advantage of this method is its ability to bypass the need for global triangulations or grids on the manifolds. Additionally, it features a highly parallel iterative scheme. To verify its efficacy, we conduct numerical experiments on some four-dimensional manifolds without and with boundary. © 2025 Society for Industrial and Applied Mathematics Publications. All rights reserved.

关键词： Domain decomposition methods

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：