检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Yan Huang Yuming Wang Yunan Zeng Liang Wang Center for Research on Intelligent Perception and Computing (CRIPAC) State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences (CASIA) School of Artificial Intelligence University of Chinese Academy of Sciences (UCAS) Chinese Academy of Sciences Artificial Intelligence Research (CAS-AIR)

ISBN: (纸本)9781713871088

Recently, the accuracy of image-text matching has been greatly improved by multimodal pretrained models, all of which are trained on millions or billions of paired images and texts. Different from them, this paper studies a new scenario as unpaired image-text matching, in which paired images and texts are assumed to be unavailable during model training. To deal with this, we propose a simple yet effective method namely Multimodal Aligned Conceptual Knowledge (MACK), which is inspired by the knowledge use in human brain. It can be directly used as general knowledge to correlate images and texts even without model training, or further fine-tuned based on unpaired images and texts to better generalize to certain datasets. In addition, we extend it as a re-ranking method, which can be easily combined with existing image-text matching models to substantially improve their performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

Cross-Modality Time-Variant Relation Learning for Generating...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jingyi Wang Jinfa Huang Can Zhang Zhidong Deng Department of Computer Science Tsinghua University Beijing China School of Electronic and Computer Engineering Peking University China Department of Computer Science Beijing National Research Center for Information Science and Technology (BNRist) THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

Dynamic scene graphs generated from video clips could help enhance the semantic visual understanding in a wide range of challenging tasks such as environmental perception, autonomous navigation, and task planning of self-driving vehicles and mobile robots. In the process of temporal and spatial modeling during dynamic scene graph generation, it is particularly intractable to learn time-variant relations in dynamic scene graphs among frames. In this paper, we propose a Time-variant Relation-aware TRansformer (TR 2 ), which aims to model the temporal change of relations in dynamic scene graphs. Explicitly, we leverage the difference of text embeddings of prompted sentences about relation labels as the supervision signal for relations. In this way, cross-modality feature guidance is realized for the learning of time-variant relations. Implicitly, we design a relation feature fusion module with a transformer and an additional message token that describes the difference between adjacent frames. Extensive experiments on the Action Genome dataset prove that our TR2 can effectively model the time-variant relations. TR2 significantly outperforms previous state-of-the-art methods under two different settings by 2.1 % and 2.6% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Context-specific miRNA regulation network predicts cancer prognosis

Context-specific miRNA regulation network predicts cancer pr...

引用

IEEE International Conference on systems Biology

作者： Xionghui Zhou Juan Liu Changning Liu Simon Rayner Fengji Liang Jingfang Ju Yinghui Li Shanguang Chen Jianghui Xiong School of Computer Science Wuhan University Wuhan China Bioinformatics Research Group Key Laboratory of Intelligent Information Processing Advanced Computing Research Laboratory Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China Bioinformatics Group State Key Laboratory of Virology Wuhan Institute of Virology Chinese Academy of Sciences (CAS) Wuhan China Bioinformatics Group and Data Coordination Center State Key Laboratory of Space Medicine Fundamentals and Application China Astronaut Research and Training Center Beijing China Department of Pathology Stony Brook University Medical Center New York USA

MicroRNAs can regulate hundreds of target genes and play a pivotal role in a broad range of biological process. However, relatively little is known about how these highly connected miRNAs-target networks are remodelled in the context of various diseases. Here we examine the dynamic alteration of context-specific miRNA regulation to determine whether modified microRNAs regulation on specific biological processes is a useful information source for predicting cancer prognosis. A new concept, Context-specific miRNA activity (CoMi activity) is introduced to describe the statistical difference between the expression level of a miRNA's target genes and non-targets genes within a given gene set (context).

关键词： Breast cancer Context Correlation Biological processes Metastasis Tumors

来源：评论

学校读者我要写书评

暂无评论

Text Semantic Analysis and intelligent Interaction in Parallel Dispatching systems for Technical Station

Text Semantic Analysis and Intelligent Interaction in Parall...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Yuantao Jiao Jian Wang Runmei Li Gang Xiong Shichao Chen School of Automation and Intelligence Beijing Jiaotong University Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China State Key Laboratory for Multimodal Artificial Intelligence Systems Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

Technical station dispatching system plays an important role in cargo operation, but due to the large number of dispatching systems and complex operation, dispatchers rely on manual experience to complete the task, and many scenarios cannot be applied in the real system. Therefore, this paper utilizes the data-driven form to establish a parallel dispatching system for technical stations, semantically analyzes text data rich in dispatcher experience, completes the Computational Experiments on the textual semantic data in the artificial dispatching system, and synchronizes the Parallel Execution of data interaction with the real dispatching system.

关键词： Training Analytical models Semantics Dispatching Digital twins Synchronization Feeds

来源：评论

学校读者我要写书评

暂无评论

An Actor-Critic Framework Deep Reinforcement Learning Approach to High-speed Train Timetable Rescheduling Problem

An Actor-Critic Framework Deep Reinforcement Learning Approa...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Zhilong Tian Runmei Li Gang Xiong Fenghua Zhu School of Automation and Intelligence Beijing Jiaotong University Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China State Key Laboratory for Multimodal Artificial Intelligence Systems Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

High-speed trains are inevitably affected by emergencies in their daily operation, which may cause the trains to fail to run according to the original planned timetable. Therefore, how to adjust the timetable of subsequent trains in emergencies is crucial for railway operations. This paper introduces a deep reinforcement learning algorithm based on an actor-critic network, which minimizes the total delay time by defining the departure order as an action. Numerical experiments are performed on the timetable of Beijing-Shanghai high-speed railway line.

关键词： Optimization models Deep reinforcement learning Rail transportation Dispatching Digital twins Delays Optimization

来源：评论

学校读者我要写书评

暂无评论

Neural piecewise-constant delay differential equations

arXiv

引用

arXiv 2022年

作者： Zhu, Qunxi Shen, Yifei Li, Dongsheng Lin, Wei Research Institute of Intelligent Complex Systems Fudan University China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong Microsoft Research Asia China School of Mathematical Sciences State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain Science Shanghai Center for Mathematical Sciences Center for Computational Systems Biology LCNBI and Research Institute of Intelligent Complex Systems Fudan University China

Continuous-depth neural networks, such as the Neural Ordinary Differential Equations (ODEs), have aroused a great deal of interest from the communities of machine learning and data science in recent years, which bridge the connection between deep neural networks and dynamical systems. In this article, we introduce a new sort of continuous-depth neural network, called the Neural Piecewise-Constant Delay Differential Equations (PCDDEs). Here, unlike the recently proposed framework of the Neural Delay Differential Equations (DDEs), we transform the single delay into the piecewiseconstant delay(s). The Neural PCDDEs with such a transformation, on one hand, inherit the strength of universal approximating capability in Neural DDEs. On the other hand, the Neural PCDDEs, leveraging the contributions of the information from the multiple previous time steps, further promote the modeling capability without augmenting the network dimension. With such a promotion, we show that the Neural PCDDEs do outperform the several existing continuousdepth neural frameworks on the one-dimensional piecewiseconstant delay population dynamics and real-world datasets, including MNIST, CIFAR10, and *** Codes 34Kxx, 93Cxx, 92B2 © 2022, CC BY.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Generalization Boosted Adapter for Open-Vocabulary Segmentation

arXiv

引用

arXiv 2024年

作者： Xu, Wenhao Wang, Changwei Feng, Xuxiang Xu, Rongtao Huang, Longzhao Zhang, Zherui Guo, Li Xu, Shibiao School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250013 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China The Aerospace Information Research Institute Chinese Academy of Sciences China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation. However, directly applying VLMs to such tasks remains challenging due to their lack of pixel-level granularity and the limited data available for fine-tuning, leading to overfitting and poor generalization. To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation. GBA comprises two core components: (1) a Style Diversification Adapter (SDA) that decouples features into amplitude and phase components, operating solely on the amplitude to enrich the feature space representation while preserving semantic consistency;and (2) a Correlation Constraint Adapter (CCA) that employs cross-attention to establish tighter semantic associations between text categories and target regions, suppressing irrelevant low-frequency "noise" information and avoiding erroneous associations. Through the synergistic effect of the shallow SDA and the deep CCA, GBA effectively alleviates overfitting issues and enhances the semantic relevance of feature representations. As a simple, efficient, and plug-and-play component, GBA can be flexibly integrated into various CLIP-based methods, demonstrating broad applicability and achieving state-of-the-art performance on multiple open-vocabulary segmentation benchmarks. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

What are the differences in yield formation among two cucumber (Cucumis sativus L.) cultivars and their F1 hybrid?

引用

Journal of Integrative Agriculture 2020年第7期19卷 1789-1801页

作者： WANG Xiu-juan KANG Meng-zhen FAN Xing-rong YANG Li-li ZHANG Bao-gui HUANG San-wen Philippe DE REFFYE WANG Fei-yue The State Key Laboratory of Management and Control for Cormplex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190P.R.China Bejjing Engineering Research Center of Intelligent Systems and Technology Institute of AutomationChinese Academy of SciencesBejing 100190P.R.China Innovation Center for Parallel Agriculture Qingdao Academy of Intelligent IndustriesQingdao 266109P.R.China School of Computer Science and Information Engineering Chongqing Technology and Business UniversityChongqing 400067P.R.China College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083P.R.China College of Land Science and Technology China Agricultural UniversityBeijing 100193P.R.China Agricultural Genomes Institute at Shenzhen Chinese Academy of Agricultural SciencesShenzhen 518124P.R.China AMAP University MontpellierCIRADCNRSINRAIRDMontpellier 34000France The School of Computer and Control Engineering University of Chinese Academy of SciencesBeijing 100049P.R.China

To elucidate the mechanisms underlying the differences in yield formation among two parents(P1 and P2) and their F1 hybrid of cucumber, biomass production and whole source–sink dynamics were analyzed using a functional–structural plant model(FSPM) that simulates both the number and size of individual organs. Observations of plant development and organ biomass were recorded throughout the growth periods of the plants. The GreenLab Model was used to analyze the differences in fruit setting, organ expansion, biomass production and biomass allocation. The source–sink parameters were estimated from the experimental measurements. Moreover, a particle swarm optimization algorithm(PSO) was applied to analyze whether the fruit setting is related to the source–sink ratio. The results showed that the internal source–sink ratio increased in the vegetative stage and reached a peak until the first fruit setting. The high yield of hybrid F1 is the compound result of both fruit setting and the internal source–sink ratio. The optimization results also revealed that the incremental changes in fruit weight result from the increases in sink strength and proportion of plant biomass allocation for fruits. The model-aided analysis revealed that heterosis is a result of a delicate compromise between fruit setting and fruit sink strength. The organlevel model may provide a computational approach to define the target of breeding by combination with a genetic model.

关键词： cucumber biomass production functional-structural plant model source-sink ratio fruit-setting PSO heterosis

来源：评论

学校读者我要写书评

暂无评论

Double Deep Q-learning for Anti-saturation Attack Problem of Warship Group

Double Deep Q-learning for Anti-saturation Attack Problem of...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wei Li Gang Xiong Hao Tao Yunjun Han Fang Wang Xisong Dong Zhen Shen State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences China China Ship Development and Design Center Wuhan China School of Control Science and Engineering (CSE) Shandong University Jinan China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

Anti-saturation attack (ASA) strategy is vital for the survival of a warship group, and attracts the focus of many researchers. In this paper, the dynamics of ASA is formulated as a Markov Decision Process (MDP) with an enhanced states space since those characters are involved, such as the formation and detection and interception areas of warship group. A reinforcement learning method (Double Deep Q-leaning, DDQN) is developed to solve the problem and deal with the curse of dimensionality whereby the cost-to-go value is calculated by a marine engagement simulation system. A heuristic defense algorithm guided by field expert knowledge is designed for comparison. The experimental results show that the DDQN method performs better in anti-saturation attack scenarios.

关键词： Industries Heuristic algorithms Digital twin Conferences Knowledge based systems Reinforcement learning Markov processes

来源：评论

学校读者我要写书评

暂无评论

Spatial Re-parameterization for N:M Sparsity

arXiv

引用

arXiv 2023年

作者： Zhang, Yuxin Xu, Mingliang Tian, Yonghong Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China Engineering Research Center of Intelligent Swarm Systems Zhengzhou China School of Electronics Engineering and Computer Science Peking University Beijing China

This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity. SpRe stems from an observation regarding the restricted variety in spatial sparsity presented in N:M sparsity compared with unstructured sparsity. Particularly, N:M sparsity exhibits a fixed sparsity rate within the spatial domains due to its distinctive pattern that mandates N non-zero components among M successive weights in the input channel dimension of convolution filters. On the contrary, we observe that conventional unstructured sparsity displays a substantial divergence in sparsity across the spatial domains, which we experimentally verify to be very crucial for its robust performance retention compared with N:M sparsity. Therefore, SpRe employs the spatial-sparsity distribution of unstructured sparsity by assigning an extra branch in conjunction with the original N:M branch at training time, which allows the N:M sparse network to sustain a similar distribution of spatial sparsity with unstructured sparsity. During inference, the extra branch can be further re-parameterized into the main N:M branch, without exerting any distortion on the sparse pattern or additional computation costs. SpRe has achieved a commendable feat by matching the performance of N:M sparsity methods with state-of-the-art unstructured sparsity methods across various benchmarks. Our project is available at https://***/zyxxmu/SpRE. © 2023, CC BY.

关键词： Convolution

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：