检索结果-内蒙古大学图书馆

Foundation models and intelligent decision-making: Progress, challenges, and perspectives

The Innovation 2025年第6期6卷

作者： Jincai Huang Yongjun Xu Qi Wang Qi (Cheems) Wang Xingxing Liang Fei Wang Zhao Zhang Wei Wei Boxuan Zhang Libo Huang Jingru Chang Liantao Ma Ting Ma Yuxuan Liang Jie Zhang Jian Guo Xuhui Jiang Xinxin Fan Zhulin An Tingting Li Aiguo Fei Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China National Engineering Research Center for Software Engineering Peking University Beijing 100871 China College of Systems Engineering National University of Defense Technology Changsha 410073 China Department of Oral Implantology Peking University School and Hospital of Stomatology Beijing 100081 China Laboratory for Big Data and Decision National University of Defense Technology Changsha 410073 China School of Automation Beijing Institute of Technology Beijing 100081 China Huazhong University of Science and Technology Wuhan 430074 China University of Chinese Academy of Sciences Beijing 100049 China State Key Laboratory of AI Safety Beijing 100190 China Department of Automation Tsinghua University Beijing 100084 China School of Information Science and Engineering Dalian Polytechnic University Dalian 116034 China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou 511453 China College of Information and Electrical Engineering China Agricultural University Beijing 100083 China State Key Laboratory of Efficient Utilization of Agricultural Water Resources Beijing 100083 China IDEA Research International Digital Economy Academy Shenzhen 518057 China School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing 100876 China

Intelligent decision-making (IDM) is a cornerstone of artificial intelligence (AI) designed to automate or augment decision processes. Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make effective and adaptive choices and decompose complex tasks into manageable steps, such as AI agents and high-level reinforcement learning. Recent advances in multimodal foundation-based approaches unify diverse input modalities—such as vision, language, and sensory data—into a cohesive decision-making process. Foundation models (FMs) have become pivotal in science and industry, transforming decision-making and research capabilities. Their large-scale, multimodal data-processing abilities foster adaptability and interdisciplinary breakthroughs across fields such as healthcare, life sciences, and education. This survey examines IDM’s evolution, advanced paradigms with FMs and their transformative impact on decision-making across diverse scientific and industrial domains, highlighting the challenges and opportunities in building efficient, adaptive, and ethical decision systems.

关键词： artificial intelligence intelligent decision-making foundation models agent large language model

来源：评论

学校读者我要写书评

暂无评论

Adaptive Feature Normalization Network for Single Image Dehazing

引用

Journal of Physics: Conference Series 2021年第1期2035卷

作者： Guangrui Hu Yueting Yang Chuansheng Yang Chao Wang Anhui Tan School of Information Engineering Zhejiang Ocean University Zhoushan 316022 China School of Mathematics and Statistics Beihua University Jilin Jilin 132013 P.R. China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhoushan 316022 China

In this paper, we design an end-to-end adaptive feature normalization network (AFN-Net) for single image dehazing. In order to fit the function that can recover haze-free images from haze images more effectively, an Adaptive Normalization module (AN) is designed, which can unify the input into the same feature space. A large number of experimental evaluations show that the proposed method is superior to the state-of-the-art (SOTA) method on the benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning the optimally coordinated routes from the statistical mechanics of polymers

arXiv

引用

arXiv 2019年

作者： Liao, Hao Wu, Xingtong Zhou, Mingyang Yeung, Chi Ho National Engineering Laboratory for big data computing systems Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Department of Science and Environmental Studies Education University of Hong Kong Hong Kong

Many major cities suffer from severe traffic congestion. Road expansion in the cites is usually infeasible, and an alternative way to alleviate traffic congestion is to coordinate the route of vehicles. Various path selection and planning algorithms are thus proposed, but most existing methods only plan paths separately and provide un-coordinated solutions. Recently, an analogy between the coordination of vehicular routes and the interaction of polymers is drawn;the spin glass theory in statistical physics is employed to optimally coordinate transportation routes. To further examine the advantages brought by path coordination, we incorporate the link congestion function developed by the Bureau of Public Roads (BPR) into the polymer routing algorithm. We then estimate in simulations the traveling time of all users saved by the polymer-BPR algorithm in randomly generated networks and real transportation networks in major cities including London, New York and Beijing. We found that a large amount of traveling time is saved in all studied networks, suggesting that the approach inspired by polymer physics is effective in minimizing the traveling time via path coordination, which is a promising tool for alleviating traffic congestions. Copyright © 2019, The Authors. All rights reserved.

关键词： Statistical mechanics

来源：评论

学校读者我要写书评

暂无评论

Substrate concentration effect on gene expression in genetic circuits with additional positive feedback

引用

Science China(Technological Sciences) 2018年第8期61卷 1175-1183页

作者： WU LuLu WANG Pei Lü JinHu Academy of Mathematics and Systems Science Chinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences School of Mathematics and Statistics Henan University School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environment and Beijing Advanced Innovation Center for Big Data and Brain Machine Intelligence Beihang University

In gene regulatory networks, gene regulation loops often occur with multiple positive feedback, multiple negative feedback and coupled positive and negative feedback forms. In above gene regulation loops, auto-activation loops are ubiquitous regulatory motifs. This paper aims to investigate a two-component dual-positive feedback genetic circuit, which consists of a double negative feedback circuit and an additional positive feedback loop(APFL). We study effect of substrate concentration on gene expression in the single and the networked systems with APFLs, respectively. We find that substrate concentration can tune stochastic switch behavior in the signal system and then we explore relationship of substrate concentration with positive feedback strength in aspect of stochastic switch behavior. Furthermore, we also discuss gene expression and stochastic switch behavior in the networked systems with APFLs. Based on analysis in the networked systems, we discover that genes express in some specific cells and do not express in the other cells when the expression achieves its steady state. These results can be used to well explain the character of regionalization in the expression of genes and the phenomenon of gene differentiation.

关键词： substrate concentration additional positive feedback loop stochastic switch behavior gene expression gene differ-entiation

来源：评论

学校读者我要写书评

暂无评论

CuckooFlow: Achieving Fast Packet Classification for Virtual OpenFlow Switching by Exploiting Network Traffic Locality

CuckooFlow: Achieving Fast Packet Classification for Virtual...

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Bing Xiong Zhixiong Hu Yao Luo Jin Wang School of Computer & Communication Engineering Changsha University of Science & Technology Changsha China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science & Technology Changsha China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

The growing trend of network virtualization leads to a widespread deployment of virtual switches in virtualized environments. However, virtual switching is confronted with great performance challenges regarding packet classification especially in OpenFlow-based software defined networks. This paper takes an insight into network traffic locality from the perspective of exact flows and wildcard flows, and propose a fast packet classification scheme CuckooFlow. In particular, we devise an active exact flow cache with cuckoo hashing to predict the respective flow entry for each arrived packet. Subsequently, we formulate its cache hit rate based on packet-in-batch arrivals, and average search length of the packet classification scheme. Finally, our proposed CuckooFlow scheme is evaluated with real network traffic traces by experiments. The experimental results indicate that our proposed scheme outperforms traditional ones Open vSwitch and CuckooDistributor in terms of cache hit rates and average search length, and contributes to promote virtual OpenFlow switching performance.

关键词： Telecommunication traffic Switches Acceleration Classification algorithms Cloud computing Virtualization Decision trees

来源：评论

学校读者我要写书评

暂无评论

Automatic Recognition of Business Process Images

Automatic Recognition of Business Process Images

引用

IEEE International Conference on Computer Science and Educational Informatization (CSEI)

作者： Qingyi Kang Yong Yu Fei Dai School of Software Yunnan University Kunming China School of Software Key Laboratory in Software Engineering of Yunnan Province Yunnan University Kunming China School of Big Data and Intelligent Engineering Southwest Forestry University Kunming China

ISBN: (纸本)9781728123097

The Business Process Modelling Notation (BPMN) is a defacto standard for modelling business processes in the early phases of systems development. The increased adoption of business process management approaches has led organizations to model large collections of BPMN business process models. The mix of constructs in BPMN business process models can lead to semantic error. The ability to take a picture of BPMN business process models and analyze the semantic correctness of BPMN business process images is thus a desirable feature. In this paper, we propose an automatic recognition method to transform BPMN business process images into Petri nets, for which efficient analysis techniques are available. The proposed recognition has been implemented as a tool, in conjunction with existing Petri net-based tools, that enables the soundness analysis of business process images. This transformation can led to the identification of deficiencies in the BPMN business process images.

关键词： Task analysis Petri nets Logic gates Image edge detection Semantics

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal CNN for video object segmentation

arXiv

引用

arXiv 2019年

作者： Xu, Kai Wen, Longyin Li, Guorong Bo, Liefeng Huang, Qingming School of Computer Science and Technology UCAS Beijing China JD Digits Mountain View CA United States Key Laboratory of Big Data Mining and Knowledge Management CAS Beijing China Inst. of Computi. Tech. CAS China

In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch. Specifically, the temporal coherence branch pretrained in an adversarial fashion from unlabeled video data, is designed to capture the dynamic appearance and motion cues of video sequences to guide object segmentation. The spatial segmentation branch focuses on segmenting objects accurately based on the learned appearance and motion cues. To obtain accurate segmentation results, we design a coarse-to-fine process to sequentially apply a designed attention module on multi-scale feature maps, and concatenate them to produce the final prediction. In this way, the spatial segmentation branch is enforced to gradually concentrate on object regions. These two branches are jointly fine-tuned on video segmentation sequences in an end-to-end manner. Several experiments are carried out on three challenging datasets (i.e., DAVIS2016, DAVIS-2017 and Youtube-Object) to show that our method achieves favorable performance against the stateof-the-arts. Code is available at https://***/longyin880815/STCNN. Copyright © 2019, The Authors. All rights reserved.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

View-based 3D model retrieval via convolutional neural networks

View-based 3D model retrieval via convolutional neural netwo...

引用

Chinese Intelligent Systems Conference, CISC 2017

作者： Du, Bowen Li, Haisheng Cai, Qiang School of Computer and Information Engineering Beijing Technology and Business University Beijing100048 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing100048 China

ISBN: (纸本)9789811064982

In this paper, we propose a multi-view fusion 3D model retrieval using convolutional neural network to solve the problem of the local perception in feature descriptor. By view pooling, we combine information from multiple views of a 3D model to eliminate the position correlation caused by the viewing angle of camera. In addition, integrating pre-processed RGB view-feature with Binary view-feature in the same model is used to generate a single model descriptor. Experiments on ETH dataset demonstrate the superiority of the proposed method. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Quantitative estimation of the factors impacting spatiotemporal variation in NPP in the Dongting Lake wetlands using Landsat time series data for the last two decades” [Ecol. Indic. 135 (2022) 108544]

引用

Ecological Indicators 2022年 144卷

作者： Meng Zhang Naiquan Yuan Hui Lin Yang Liu Huaiqing Zhang Research Center of Forestry Remote Sensing & Information Engineering Central South University of Forestry & Technology Changsha 410004 China Key Laboratory of State Forestry Administration on Forest Resources Management and Monitoring in Southern Area Changsha 410004 China Key Laboratory of Forestry Remote Sensing Based Big Data & Ecological Security for Hunan Province Changsha 410004 China Hunan Academy of Geosciences Planning and Design Co. Ltd Changsha 410118 China Research Institute of Forest Resources Information Techniques Chinese Academy of Forestry Beijing 100091 China

来源：评论

学校读者我要写书评

暂无评论

FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On

FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On

引用

International Conference on Computer Vision (ICCV)

作者： Haoye Dong Xiaodan Liang Xiaohui Shen Bowen Wu Bing-Cheng Chen Jian Yin School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R.China School of Intelligent Systems Engineering Sun Yat-sen University ByteDance AI Lab

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Beyond current image-based virtual try-on systems that have attracted increasing attention, we move a step forward to developing a video virtual try-on system that precisely transfers clothes onto the person and generates visually realistic videos conditioned on arbitrary poses. Besides the challenges in image-based virtual try-on (e.g., clothes fidelity, image synthesis), video virtual try-on further requires spatiotemporal consistency. Directly adopting existing image-based approaches often fails to generate coherent video with natural and realistic textures. In this work, we propose Flow-navigated Warping Generative Adversarial Network (FW-GAN), a novel framework that learns to synthesize the video of virtual try-on based on a person image, the desired clothes image, and a series of target poses. FW-GAN aims to synthesize the coherent and natural video while manipulating the pose and clothes. It consists of: (i) a flow-guided fusion module that warps the past frames to assist synthesis, which is also adopted in the discriminator to help enhance the coherence and quality of the synthesized video; (ii) a warping net that is designed to warp clothes image for the refinement of clothes textures; (iii) a parsing constraint loss that alleviates the problem caused by the misalignment of segmentation maps from images with different poses and various clothes. Experiments on our newly collected dataset show that FW-GAN can synthesize high-quality video of virtual try-on and significantly outperforms other methods both qualitatively and quantitatively.

关键词： Integrated circuits Generators Gallium nitride Three-dimensional displays Image generation Computational modeling Visualization

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：