检索结果-内蒙古大学图书馆

Generation-based contrastive model with semantic alignment for generalized zero-shot learning

IMAGE AND VISION computing 2023年第1期137卷

作者： Yang, Jingqi Shen, Qi Xie, Cheng Ynunan Univ Kunming Peoples R China

Generalized zero-shot learning (GZSL) is an important research area in image computing, video processing, multimedia understanding, and other visual computing tasks. GZSL normally uses transferable semantic features to represent the visual features to predict unseen classes without training the unseen samples. The state-of-the-art zero-shot learning methods combine Generative Adversarial Network (GAN) and Contrastive Learning (CL) together to deeply transfer semantic features to visual features. However, the combined GAN module and CL module inevitably encounter the "semantic-visual inconsistent problem" in both the feature-generating process and the contrastive learning process. To handle the above problems, we propose the generation-based contrastive model with semantic alignment for generalized zero-shot learning. The proposed network is based on existing ZSL models combining GAN and CL, but with two additional alignment modules that are Feedback Alignment Module (FAM) and Negative sample Alignment Module (NAM). FAM applies an MLP (Multilayer Perceptron) to align the synthesized visual feature back to its semantic feature for keeping the semantic-visual consistency in the generator. NAM provides a new contrastive learning mechanism to align the negative pairs for keeping semanticvisual consistency during contrastive learning. Experimental results on massive real-world datasets show the proposed method achieves the new state-of-the-art in the field of generalized zero-shot learning. The source code of the proposed method is available athttps://***/yangjingqi99/GCSA.

关键词： Zero-shot learning Image classification visual computing Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Real estate pricing prediction via textual and visual features

引用

MACHINE VISION AND APPLICATIONS 2023年第6期34卷 126-126页

作者： Yousif, Amira Baraheem, Samah Vaddi, Sai Surya Patel, Vatsa S. Shen, Ju Nguyen, Tam V. Univ Dayton Dept Comp Sci Dayton OH 45469 USA

The real estate industry relies heavily on accurately predicting the price of a house based on numerous factors such as size, location, amenities, and season. In this study, we explore the use of machine learning techniques for predicting house prices by considering both visual cues and estate attributes. We collected a dataset (REPD-3000) of 3000 houses across 74 cities in the USA and annotated 14 estate attributes and five visual images for each house's exterior, interior-living room, kitchen, bedroom, and bathroom. We extracted features from the input images using convolutional neural network (CNN) and fed them along with the estate attributes into a multi-kernel deep learning regression model to predict the house price. Our model outperformed baseline models in extensive experiments, achieving the best result with a mean absolute error (MAE) of 16.60. We compared our model with a multi-kernel support vector regression and analyzed the impact of incorporating individual feature sets. In future, we plan to address class imbalance by having the same number of houses in each class and explore feature engineering for improving the model's performance.

关键词： House price prediction Multi-kernel learning visual computing Estate attributes Computer vision Machine learning Deep regression

来源：评论

学校读者我要写书评

暂无评论

Next Generation Semantic and Spatial Joint Perception——Neural Metric-Semantic Understanding

引用

ZTE Communications 2021年第1期19卷 61-71页

作者： ZHU Fang State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen 518057China ZTE Corporation Shenzhen 518057China

Efficient perception of the real world is a long-standing effort of computer ***⁃ern visual computing techniques have succeeded in attaching semantic labels to thousands of daily objects and reconstructing dense depth maps of complex ***,simultaneous se⁃mantic and spatial joint perception,so-called dense 3D semantic mapping,estimating the 3D ge⁃ometry of a scene and attaching semantic labels to the geometry,remains a challenging problem that,if solved,would make structured vision understanding and editing more widely ***,progress in computer vision and machine learning has motivated us to pursue the capability of understanding and digitally reconstructing the surrounding *** metric-se⁃mantic understanding is a new and rapidly emerging field that combines differentiable machine learning techniques with physical knowledge from computer vision,e.g.,the integration of visualinertial simultaneous localization and mapping(SLAM),mesh reconstruction,and semantic un⁃*** this paper,we attempt to summarize the recent trends and applications of neural metric-semantic *** with an overview of the underlying computer vision and machine learning concepts,we discuss critical aspects of such perception ***⁃ly,our emphasis is on fully leveraging the joint semantic and 3D *** on,many im⁃portant applications of the perception capability such as novel view synthesis and semantic aug⁃mented reality(AR)contents manipulation are also ***,we conclude with a dis⁃cussion of the technical implications of the technology under a 5G edge computing scenario.

关键词： visual computing semantic and spatial joint perception dense 3D semantic map⁃ping neural metric-semantic understanding

来源：评论

学校读者我要写书评

暂无评论

Graph Convolution Algorithm Based on visual Selectivity and Point Cloud Analysis Application

引用

TRAITEMENT DU SIGNAL 2022年第5期39卷 1507-1516页

作者： Zhao, Yanming Su, Guoan Yang, Hong Zhao, Tianshuai Jin, Songwen Yang, Jianing Hebei Normal Univ Nationalities Chengde 067000 Peoples R China

The graph convolution algorithm currently suffers from the drawback of not fusing point cloud information and point cloud topology structure information based on visual selectivity features and using absolute quantities like distance as features, resulting in the algorithm losing geometric invariance. This information serves as the foundation for the "Graph Convolution Algorithm Based on visual Selectivity and Application of Point Cloud Analysis". In order to propose a graph convolutional kernel and its design method based on visual selectivity, the algorithm analyzes the global characteristics of the point cloud "close in the vicinity and sparse in the distance," the local selectivity of the point cloud topology structure in the neighborhood, and the consistency between features and visual selectivity of primates. By combining point cloud information with point cloud topology structure information features, a graph convolution computation method was built, and the algorithm's geometric invariance was confirmed. The recognition and semantic segmentation performances of the approach in this study were verified using the ModelNet40 and ShapeNetPart data sets in comparison to the PointNet, PointNet++, DGCNN, KPConv, and 3D-GCN algorithms. The experimental design demonstrates that the algorithm presented in this research is accurate and practical, has geometric invariance, and performs better at semantic segmentation and recognition than conventional algorithms.

关键词： visual computing visual selectivity graph convolution analysis receptive field point cloud topology support set

来源：评论

学校读者我要写书评

暂无评论

Morphological analysis of historical lanscapes based on cultural DNA approach

引用

Digital Applications in Archaeology and Cultural Heritage 2023年 30卷

作者： Goodarzi, Parichehr Ansari, Mojtaba Mahdavinejad, Mohammadjavad Russo, Alessio Haghighatbin, Mahdi Pour Rahimian, Farzad Department of Architecture Faculty of Art & Architecture Tarbiat Modares University Tehran Iran School of Arts University of Gloucestershire Francis Close Hall Campus Swindon Road Cheltenham GL50 4AZ United Kingdom School of Computing Engineering & Digital Technologies Teesside University Middlesbrough United Kingdom

Recent trends in landscape architecture investigate new approaches, methods, and technologies to understand, monitor, manage, continuity, and sustainably develop heritage landscapes. Cultural DNA (CD) represents designs' transferable geometric, behavioural and functional properties. The morphological structure of Persian historical gardens possesses discoverable hidden patterns, computable through the CD's mathematical and computational models. This study aims to investigate and discover effective parameters in the spatial structure of historical Persian gardens using Space Syntax. Six Persian Gardens were surveyed, and spatial structures were analysed using DepthMap10 software. The results show that these spaces follow meaningful mathematical patterns and rules that can be formulated in the context of generative processes and generalized for the evolutionary continuity of gardens. However, further research is proposed to develop more advanced computational methods, such as artificial intelligence (AI) algorithms and AI-based decision support tools, to help to generate design scenarios and to transmit culture through the design process. © 2023

关键词： Cultural DNA (CD) Historic Persian garden Pattern language Space syntax Unmanned aerial vehicles (UAVs) visual computing

来源：评论

学校读者我要写书评

暂无评论

Design and Application of a Slow Feature Algorithm Coupling visual Selectivity and Multiple Long Short-Term Memory Networks

引用

TRAITEMENT DU SIGNAL 2021年第5期38卷 1521-1530页

作者： Zhao, Yanming Yang, Hong Su, Guoan Hebei Normal Univ Nationalities Dept Math & Comp Sci Chengde 067000 Peoples R China

In the traditional slow feature analysis (SFA), the expansion of polynomial basis function lacks the support of visual computing theories for primates, and cannot learn the uniform, continuous long short-term features through selective visual mechanism. To solve the defects, this paper designs and implements a slow feature algorithm coupling visual selectivity and multiple long short-term memory networks (LSTMs). Inspired by the visual invariance theory of natural images, this paper replaces the principal component analysis (PCA) of traditional SFA algorithm with myTICA (TICA: topologically independent component analysis) to extract image invariant Gabor basis functions, and initialize the space and series of basis functions. In view of the ability of the LSTM to learn long and short-term features, four LSTM algorithms were constructed to separately predict the long and short-term visual selectivity features of Gabor basis functions from the basis function series, and combine the functions into a new basis function, thereby solving the defect of polynomial prediction algorithms. In addition, a Lipschitz consistency condition was designed, and used to develop an approximate orthogonal pruning technique, which optimizes the prediction basis functions, and constructs a hyper-complete space for the basis function. The performance of our algorithm was evaluated by three metrics and mySFA's classification method. The experimental results show that our algorithm achieved a good prediction effect on INRIA Holidays dataset, and outshined SFA, graph-based SFA (SFA), TICA, and myTICA in accuracy and feasibility;when the threshold was 6, the recognition rate of our algorithm was 99.98%, and the false accept rate (FAR) and false reject rate (FRR) were both smaller than 0.02%, indicating the strong classification ability of our approach.

关键词： slow features long short-term memory network (LSTM) Lipshitz condition visual selectivity Gabor visual computing

来源：评论

学校读者我要写书评

暂无评论

Vision Tracking: A Survey of the State-of-the-Art

引用

SN Computer Science 2020年第1期1卷 57页

作者： Dutta, Anjan Mondal, Atreyee Dey, Nilanjan Sen, Soumya Moraru, Luminiţa Hassanien, Aboul Ella Department of Information Technology Techno International New Town (Formerly known as Techno India College of Technology) Kolkata India A.K. Choudhury School of Information Technology University of Calcutta Kolkata India Department of Physics Faculty of Sciences Univ. “Dunarea de Jos” Str. Domneasca nr. 111 Galati 800201 Romania Information Technology Department Faculty of Computers and Information Cairo University Giza Egypt

Vision tracking is a well-studied framework in vision computing. Developing a robust visual tracking system is challenging because of the sudden change in object motion, cluttered background, partial occlusion and camera motion. In this study, the state-of-the art visual tracking methods are reviewed and different categories are discussed. The overall visual tracking process is divided into four stages—object initialization, appearance modeling, motion estimation, and object localization. Each of these stages is briefly elaborated and related researches are discussed. A rapid growth of visual tracking algorithms is observed in last few decades. A comprehensive review is reported on different performance metrics to evaluate the efficiency of visual tracking algorithms which might help researchers to identify new avenues in this area. Various application areas of the visual tracking are also discussed at the end of the study. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Motion estimation Object localization Object motion visual computing visual tracking

来源：评论

学校读者我要写书评

暂无评论

Efficient exponential time integration for simulating nonlinear coupled oscillators

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2021年 391卷 113429-113429页

作者： Luan, Vu Thai Michels, Dominik L. Mississippi State Univ Dept Math & Stat 410 Allen Hall175 Presidents Circle Mississippi State MS 39762 USA KAUST Visual Comp Ctr Computat Sci Grp Bldg 1 Thuwal 23955 Saudi Arabia

In this paper, we propose an advanced time integration technique associated with explicit exponential Rosenbrock-based methods for the simulation of large stiff systems of nonlinear coupled oscillators. In particular, a novel reformulation of these systems is introduced and a general family of efficient exponential Rosenbrock schemes for simulating the reformulated system is derived. Moreover, we show the required regularity conditions and prove the convergence of these schemes for the system of coupled oscillators. We present an efficient implementation of this new approach and discuss several applications in scientific and visual computing. The accuracy and efficiency of our approach are demonstrated through a broad spectrum of numerical examples, including a nonlinear Fermi-Pasta-Ulam-Tsingou model, elastic and nonelastic deformations as well as collision scenarios focusing on relevant aspects such as stability and energy conservation, large numerical stiffness, high fidelity, and visual accuracy. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Systems of coupled oscillators Exponential Rosenbrock integrators Accurate and efficient simulation visual computing

来源：评论

学校读者我要写书评

暂无评论

PeruFoodNet: A unique dataset of traditional peruvian food for image recognition systems and allergenic ingredient inference

引用

Data in Brief 2025年 60卷

作者： María Franchesca Arzola Gutierrez Edgar Alexander Canchari Muñoz Edwin Jonathan Escobedo Cárdenas Carrera de Ingeniería de Sistemas Facultad de Ingeniería Universidad de Lima. Av. Javier Prado Este 4600 Santiago de Surco 15023 Perú

Peruvian cuisine has won numerous international awards, attracting tourists from around the world to Peru to experience its diverse culinary offerings. However, some dishes contain ingredients that can trigger allergic reactions, posing a potential health risk for visitors. To address this, we created PeruFoodNet, a dataset featuring 4,000 images of traditional Peruvian dishes. The dataset includes 40 of the most popular dishes, such as Ceviche and Anticuchos, with 100 images of each dish. The images of the dishes have been captured from various angles, settings, lighting conditions, dimensions and backgrounds. To gather these images, we prepared the dishes ourselves, purchased some from restaurants, and received contributions from external users over a two-month period. However, most of the images were captured by the authors of the dataset. The dataset is publicly available and can be valuable for research in image recognition and classification using Computer Science techniques, such as Deep Learning. Additionally, it can aid in identifying allergenic ingredients in dishes by linking the dish’s image to a list of ingredients through a technological platform, such as a chatbot or an app.

关键词： Gastronomy Food allergens Food classification visual computing Deep learning

来源：评论

学校读者我要写书评

暂无评论

visual Analytics Approach to Comprehensive Meteorological Time-Series Analysis

引用

DATA 2020年第4期5卷 94-94页

作者： Vuckovic, Milena Schmidt, Johanna VRVis Zentrum Virtual Real & Visualisierung Forsc A-1220 Vienna Austria

In some of the domain-specific sectors, such as the climate domain, the provision of publicly available present-day high-resolution meteorological time series is often quite limited or completely lacking. This repeatedly leads to excessive deployment of synthetically generated (historical) meteorological time series (TMY) to support thermal performance assessments on both building and urban scale. These datasets are generally a misrepresentation of current weather variability, which may lead to erroneous inferences drawn from modelling results. In this regard, we outline the application potential of a visual analytics approach in the context of data quality assessment and validation of TMYs. For this purpose, we deployed a standalone visual analytics tool Visplore, enriched with interlinked dashboards, customizable visualizations, and intuitive workflows, to support continuous interaction and early visual feedback. Driven by such integrated visual representations and visual interactions to enhance the analytical reasoning process, we were able to detect critical multifaceted discrepancies, on different levels of granularity, between TMY and present-day meteorological time series and synthetize them into cohesive patterns and insights. These mainly entailed diverging temporal trends and event time lags, under- and overestimation of warming and cooling regimes, respectively, and seasonal discrepancies, in particular meteorological parameters, to name a few.

关键词： visual analytics interactive visualization visual computing data quality climate data

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：