检索结果-内蒙古大学图书馆

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Fu, Bin Yu, Fanghua Liu, Anran Wang, Zixuan Wen, Jie He, Junjun Qiao, Yu Chinese Acad Sci Shenzhen Inst Adv Technol ShenZhen Key Lab Comp Vis & Pattern Recognit Shenzhen Peoples R China Shanghai Artificial Intelligence Lab Shanghai Peoples R China Univ Hong Kong Hong Kong Peoples R China Harbin Inst Technol Shenzhen Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Few-shot font generation (FFG) produces stylized font images with a limited number of reference samples, which can significantly reduce labor costs in manual font designs. Most existing FFG methods follow the style-content disentanglement paradigm and employ the generative Adversarial Network (GAN) to generate target fonts by combining the decoupled content and style representations. The complicated structure and detailed style are simultaneously generated in those methods, which may be the sub-optimal solutions for FFG task. Inspired by most manual font design processes of expert designers, in this paper, we model font generation as a multi-stage generative process. Specifically, as the injected noise and the data distribution in diffusion models can be well-separated into different sub-spaces, we are able to incorporate the font transfer process into these models. Based on this observation, we generalize diffusion methods to model font generative process by separating the reverse diffusion process into three stages with different functions: The structure construction stage first generates the structure information for the target character based on the source image, and the font transfer stage subsequently transforms the source font to the target font. Finally, the font refinement stage enhances the appearances and local details of the target font images. Based on the above multi-stage generative process, we construct our font generation framework, named MSD-Font, with a dual-network approach to generate font images. The superior performance demonstrates the effectiveness of our model. The code is available at: https://***/fubinfb/MSD-Font

关键词： Diffusion model Few-shot Font Generation probabilistic generative model

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity-Aware Recurrent Neural Network for Hyperspectral and Multispectral Image Fusion

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2022年第4期16卷 649-665页

作者： Lu, Ruiying Chen, Bo Sun, Jianqiao Chen, Wenchao Wang, Penghui Chen, Yuanwei Liu, Hongwei Varshney, Pramod K. Xidian Univ Collaborat Innovat Ctr Informat Sensing & Underst Natl Lab Radar Signal Proc Xian 710071 Peoples R China China Acad Space Technol Beijing 100081 Peoples R China Syracuse Univ Dept Elect Engn & Comp Sci Syracuse NY 13244 USA

Due to the hardware limitations of remote imaging sensors, it is challenging to acquire images with high resolution in both the spatial and spectral domains. An effective and economical way to obtain high-resolution hyperspectral images (HR HSI) is to fuse low-resolution hyperspectral images (LR HSI) and high-resolution multispectral images (HR MSI). However, most existing deep learning based fusion methods employ the same network for all of the spectra without exploring their complex regional heterogeneity of hyperspectral characteristics. Taking various intrinsic spatial and spectral characteristics across different pixels into consideration, this paper proposes a mixture of recurrent neural networks (RNNs) under the variational probabilistic framework for spatial and spectral resolution enhancement. More specifically, we firstly cluster spectral characteristics into different groups, and employ different RNN experts for various spectra generation under the guidance of clustering. Moreover, a cluster-specific learnable Gaussian prior is proposed to provide a prior knowledge of heterogeneity. Further, an online variational inference scheme is derived for end-to-end optimization. Extensive experimental results demonstrate the effectiveness and efficiency of the proposed model on both synthetic and real datasets, compared with state-of-the-art unsupervised fusion methods.

关键词： Hyperspectral imaging Spatial resolution Tensors Bayes methods probabilistic logic Optimization Mathematical models Dirichlet process mixture model clustering recurrent neural network probabilistic generative model hyperspectral imaging image fusion

来源：评论

学校读者我要写书评

暂无评论

Symbol Emergence as Inter-personal Categorization with Head-to-head Latent Word

Symbol Emergence as Inter-personal Categorization with Head-...

引用

IEEE International Conference on Development and Learning (ICDL)

作者： Furukawa, Kazuma Taniguchi, Akira Hagiwara, Yoshinobu Taniguchi, Tadahiro Ritsumeikan Univ Grad Sch Informat Sci & Engn Kusatsu Japan Ritsumeikan Univ Coll Informat Sci & Engn Kusatsu Japan

ISBN: (数字)9781665413114

ISBN: (纸本)9781665413114

In this study, we propose a head-to-head type (H2H-type) inter-personal multimodal Dirichlet mixture (Inter-MDM) by modifying the original Inter-MDM, which is a probabilistic generative model that represents the symbol emergence between two agents as multiagent multimodal categorization. A Metropolis-Hastings method-based naming game based on the Inter-MDM enables two agents to collaboratively perform multimodal categorization and share signs with a solid mathematical foundation of convergence. However, the conventional Inter-MDM presumes a tail-to-tail connection across a latent word variable, causing inflexibility of the further extension of Inter-MDM for modeling a more complex symbol emergence. Therefore, we propose herein a head-to-head type (H2H-type) Inter-MDM that treats a latent word variable as a child node of an internal variable of each agent in the same way as many prior studies of multimodal categorization. On the basis of the H2H-type Inter-MDM, we propose a naming game in the same way as the conventional Inter-MDM. The experimental results show that the H2H-type Inter-MDM yields almost the same performance as the conventional Inter-MDM from the viewpoint of multimodal categorization and sign sharing.

关键词： symbol emergence multimodal categorization probabilistic generative model emergent communication language game

来源：评论

学校读者我要写书评

暂无评论

Hippocampal formation-inspired global self-localization: quick recovery from the kidnapped robot problem from an egocentric perspective

引用

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 2024年 18卷 1398851页

作者： Nakashima, Takeshi Otake, Shunsuke Taniguchi, Akira Maeyama, Katsuyoshi El Hafi, Lotfi Taniguchi, Tadahiro Yamakawa, Hiroshi Ritsumeikan Univ Grad Sch Informat Sci & Engn Osaka Japan Osaka Univ Grad Sch Informat Sci & Technol Osaka Japan Ritsumeikan Univ Coll Informat Sci & Engn Osaka Japan Ritsumeikan Univ Res Org Sci & Technol Shiga Japan Whole Brain Architecture Initiat Tokyo Japan Univ Tokyo Sch Engn Tokyo Japan RIKEN Ctr Adv Intelligence Project Tokyo Japan

It remains difficult for mobile robots to continue accurate self-localization when they are suddenly teleported to a location that is different from their beliefs during navigation. Incorporating insights from neuroscience into developing a spatial cognition model for mobile robots may make it possible to acquire the ability to respond appropriately to changing situations, similar to living organisms. Recent neuroscience research has shown that during teleportation in rat navigation, neural populations of place cells in the cornu ammonis-3 region of the hippocampus, which are sparse representations of each other, switch discretely. In this study, we construct a spatial cognition model using brain reference architecture-driven development, a method for developing brain-inspired software that is functionally and structurally consistent with the brain. The spatial cognition model was realized by integrating the recurrent state-space model, a world model, with Monte Carlo localization to infer allocentric self-positions within the framework of neuro-symbol emergence in the robotics toolkit. The spatial cognition model, which models the cornu ammonis-1 and -3 regions with each latent variable, demonstrated improved self-localization performance of mobile robots during teleportation in a simulation environment. Moreover, it was confirmed that sparse neural activity could be obtained for the latent variables corresponding to cornu ammonis-3. These results suggest that spatial cognition models incorporating neuroscience insights can contribute to improving the self-localization technology for mobile robots. The project website is https://***/HF-IGL/.

关键词： allocentric brain-inspired AI egocentric kidnapped robot problem Monte Carlo localization probabilistic generative model world model

来源：评论

学校读者我要写书评

暂无评论

Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network

引用

NEURAL NETWORKS 2021年 134卷 64-75页

作者： Demin, V. A. Nekhaev, D., V Surazhevsky, I. A. Nikiruy, K. E. Emelyanov, A., V Nikolaev, S. N. Rylkov, V. V. Kovalchuk, M., V Kurchatov Inst Natl Res Ctr Moscow Russia Moscow Inst Phys & Technol Dolgoprudnyi Russia Kotelnikov Inst Radio Engn & Elect RAS Fryazino 141190 Moscow Region Russia Lomonosov Moscow State Univ Moscow Russia

This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB)(x)(LiNbO3)(1-x) nanocomposite memristor. Next, the learning convergence to a solution of binary clusterization task is analyzed in a wide range of memristive STDP parameters for a single-layer fully connected feedforward SNN. The memristive STDP behavior supplying convergence in this simple task is shown also to provide it in the handwritten digit recognition domain by the more complex SNN architecture with a Winner-Take-All competition between neurons. To investigate basic conditions necessary for training convergence, an original probabilistic generative model of a rate-based single layer network with independent or competing neurons is built and thoroughly analyzed. The main result is a statement of "correlation growth-anticorrelation decay"principle which prompts near optimal policy to configure model parameters. This principle is in line with requiring the binary clusterization convergence which can be defined as the necessary condition for optimal learning and used as the simple benchmark for tuning parameters of various neural network realizations with population-rate information coding. At last, a heuristic algorithm is described to experimentally find out the convergence conditions in a memristive SNN, including robustness to a device variability. Due to the generality of the proposed approach, it can be applied to a wide range of memristors and neurons of softwareor hardware-based rate-coding single-layer SNNs when searching for local rules that ensure their unsupervised learning convergence in a pattern recognition task domain. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Memristor Hardware analog neuron Spiking neural network Memristive STDP Unsupervised learning probabilistic generative model

来源：评论

学校读者我要写书评

暂无评论

Statistical Inference of Diffusion Networks

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2021年第2期33卷 742-753页

作者： Huang, Hao Yan, Qian Chen, Lu Gao, Yunjun Jensen, Christian S. Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Aalborg Univ Dept Comp Sci DK-9220 Aalborg Denmark Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310027 Peoples R China

To infer structures in diffusion networks, existing approaches mostly need to know not only the final infection statuses of network nodes, but also the exact times when infections occur. In contrast, in many real-world settings, such as disease propagation, monitoring exact infection times is often infeasible due to a high cost. We investigate the problem of how to learn diffusion network structures based on only the final infection statuses of nodes. Instead of utilizing sequences of timestamps to determine potential parent-child influence relationships between nodes, we propose to find influence relationships with high statistical significance. To this end, we design a probabilistic generative model of the final infection statuses to quantitatively measure the likelihood of potential structures of the objective diffusion network, taking into account network complexity. Based on this model, we can infer an appropriate number of most probable parent nodes for each node in the network. Furthermore, to reduce redundant inference computations, we are able to preclude insignificant candidate parent nodes from being considered during inferencing, if their infections have little correlation with the infections of the corresponding child nodes. Extensive experiments on both synthetic and real-world networks offer evidence that the proposed approach is effective and efficient.

关键词： Diffusion network influence relationship infection timestamp probabilistic generative model

来源：评论

学校读者我要写书评

暂无评论

Emotion prediction as computation over a generative theory of mind

引用

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES 2023年第2251期381卷 20220047-20220047页

作者： Houlihan, Sean Dae Kleiman-Weiner, Max Hewitt, Luke B. Tenenbaum, Joshua B. Saxe, Rebecca MIT Dept Brain & Cognit Sci Cambridge MA 02139 USA Harvard Univ Dept Psychol Cambridge MA USA

From sparse descriptions of events, observers can make systematic and nuanced predictions of what emotions the people involved will experience. We propose a formal model of emotion prediction in the context of a public high-stakes social dilemma. This model uses inverse planning to infer a person's beliefs and preferences, including social preferences for equity and for maintaining a good reputation. The model then combines these inferred mental contents with the event to compute 'appraisals': whether the situation conformed to the expectations and fulfilled the preferences. We learn functions mapping computed appraisals to emotion labels, allowing the model to match human observers' quantitative predictions of 20 emotions, including joy, relief, guilt and envy. model comparison indicates that inferred monetary preferences are not sufficient to explain observers' emotion predictions;inferred social preferences are factored into predictions for nearly every emotion. Human observers and the model both use minimal individualizing information to adjust predictions of how different people will respond to the same event. Thus, our framework integrates inverse planning, event appraisals and emotion concepts in a single computational model to reverse-engineer people's intuitive theory of *** article is part of a discussion meeting issue 'Cognitive artificial intelligence'.

关键词： emotion inverse planning theory of mind social intelligence affective computing probabilistic generative model

来源：评论

学校读者我要写书评

暂无评论

Intrinsic Gaussian process on unknown manifolds with probabilistic metrics

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 4739-4780页

作者： Mu Niu Zhenwen Dai Pokman Cheung Yizhu Wang School of Mathematics and Statistics University of Glasgow UK Spotify London UK London UK School of Mathematics and Statistics University of Glasgow UK

This article presents a novel approach to construct Intrinsic Gaussian Processes for regression on unknown manifolds with probabilistic metrics (GPUM ) in point clouds. In many real world applications, one often encounters high dimensional data (e.g.'point cloud data') centered around some lower dimensional unknown manifolds. The geometry of manifold is in general different from the usual Euclidean geometry. Naively applying traditional smoothing methods such as Euclidean Gaussian Processes (GPs) to manifold-valued data and so ignoring the geometry of the space can potentially lead to highly misleading predictions and inferences. A manifold embedded in a high dimensional Euclidean space can be well described by a probabilistic mapping function and the corresponding latent space. We investigate the geometrical structure of the unknown manifolds using the Bayesian Gaussian Processes latent variable models(B-GPLVM) and Riemannian geometry. The distribution of the metric tensor is learned using B-GPLVM. The boundary of the resulting manifold is defined based on the uncertainty quantification of the mapping. We use the probabilistic metric tensor to simulate Brownian Motion paths on the unknown manifold. The heat kernel is estimated as the transition density of Brownian Motion and used as the covariance functions of GPUM. The applications of GPUM are illustrated in the simulation studies on the Swiss roll, high dimensional real datasets of WiFi signals and image data examples. Its performance is compared with the Graph Laplacian GP, Graph Matérn GP and Euclidean GP.

关键词： implicit manifold Gaussian process heat kernel Brownian motion probabilistic generative model

来源：评论

学校读者我要写书评

暂无评论

On Disambiguating Authors: Collaboration Network Reconstruction in a Bottom-up Manner 37

On Disambiguating Authors: Collaboration Network Reconstruct...

引用

37th IEEE International Conference on Data Engineering (IEEE ICDE)

作者： Li, Na Zhu, Renyu Zhou, Xiaoxu He, Xiangnan Cai, Wenyuan Gao, Ming Zhou, Aoying East China Normal Univ Sch Data Sci & Engn Shanghai Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei Peoples R China Shanghai Hypers Data Technol Inc Shanghai Peoples R China East China Normal Univ Sch Stat KLATASDS MOE Shanghai Peoples R China

ISBN: (纸本)9781728191843

Author disambiguation arises when different authors share the same name, which is a critical task in digital libraries, such as DBLP, CiteULike, CiteSeerX, etc. While the state-of-the-art methods have developed various paper embedding-based methods performing in a top-down manner, they primarily focus on the ego-network of a target name and overlook the low-quality collaborative relations existed in the ego-network. Thus, these methods can be suboptimal for disambiguating authors. In this paper, we model the author disambiguation as a collaboration network reconstruction problem, and propose an incremental and unsupervised author disambiguation method, namely IUAD, which performs in a bottom-up manner. Initially, we build a stable collaboration network based on stable collaborative relations. To further improve the recall, we build a probabilistic generative model to reconstruct the complete collaboration network. In addition, for newly published papers, we can incrementally judge who publish them via only computing the posterior probabilities. We have conducted extensive experiments on a large-scale DBLP dataset to evaluate IUAD. The experimental results demonstrate that IUAD not only achieves the promising performance, but also outperforms comparable baselines significantly. Codes are available at https://***/papergitgit/IUAD.

关键词： Collaboration Network Author Disambiguation probabilistic generative model Exponential Family

来源：评论

学校读者我要写书评

暂无评论

STARec: Adaptive Learning with Spatiotemporal and Activity Influence for POI Recommendation

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2022年第4期40卷 65-65页

作者： Ji, Weiyu Meng, Xiangwu Zhang, Yujie Beijing Univ Posts & Telecommun Sch Comp Sci Natl Pilot Software Engn Sch 10 Xi Tucheng Rd Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Beijing Key Lab Intelligent Telecommun Software & 10 Xi Tucheng Rd Beijing 100876 Peoples R China

POI recommendation has become an essential means to help people discover attractive places. Intuitively, activities have an important impact on users' decision-making, because users select POIs to attend corresponding activities. However, many existing studies ignore the social motivation of user behaviors and regard all check-ins as influenced only by individual user interests. As a result, they cannot model user preferences accurately, which degrades recommendation effectiveness. In this article, from the perspective of activities, this study proposes a probabilistic generative model called STARec. Specifically, based on the social effect of activities, STARec defines users' social preferences as distinct from their individual interests and combines these with individual user activity interests to effectively depict user preferences. Moreover, the inconsistency between users' social preferences and their decisions is modeled. An activity frequency feature is introduced to acquire accurate user social preferences because of close correlation between these and the key impact factor of corresponding check-ins. An alias sampling-based training method was used to accelerate training. Extensive experiments were conducted on two real-world datasets. Experimental results demonstrated that the proposed STARec model achieves superior performance in terms of high recommendation accuracy, robustness to data sparsity, effectiveness in handling cold-start problems, efficiency, and interpretability.

关键词： Personalized POI recommendation social motivation of user behaviors social effect of activities spatiotemporal activity influence inconsistency frequency feature of activities probabilistic generative model Gaussian LDA LightLDA

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：