检索结果-内蒙古大学图书馆

Group-pair deep feature learning for multi-view 3d model retrieval

APPLIEd INTELLIGENCE 2022年第2期52卷 2013-2022页

作者： Chen, Xiuxiu Liu, Li Zhang, Long Zhang, Huaxiang Meng, Lili Liu, dongmei Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China

This paper employs Convolutional Neural Networks with pooling module to extract view descriptor of 3d model, and proposes the Group-Pair deep Feature Learning method for multi-view 3d model retrieval. In the method, view descriptor is learned by the supervised autoencoder and multi-label discriminator to further mine the latent feature and category feature of 3d model. To enhance the discriminative capability of model features, we give the Margin Center Loss that minimizes the intra-class distance and maximize the inter-class distance. Experimental results on modelNet10 and modelNet40 datasets demonstrate that the proposed method significantly outperforms the state-of-the-art methods.

关键词： deep feature learning Margin Center Loss 3d model retrieval

来源：评论

学校读者我要写书评

暂无评论

3d Bessel moments for 3d model retrieval

引用

MULTIMEdIA TOOLS ANd APPLICATIONS 2022年第24期82卷 38011页

作者： Ma, Ziping Li, Tingting Zhou, Jie Yang, Ke North Minzu Univ Sch Math & Informat Sci Yinchuan Ningxia Peoples R China North Minzu Univ Sch Comp Sci & Engn Yinchuan Ningxia Peoples R China

Three-dimensional (3d) model retrieval and shape recognition are focus of research with the development of big data technology and the increasing application of 3d model in practical application recently. However, there still exist some challenges, such as the diculties of designing more accurate and efficient description with low dimension, geometric invariance and strong robustness in feature extraction. In virtue of this, we propose 3d Bessel moments based on polar representation by the first-class Bessel polynomial. The 3d Bessel moments inherit the properties of and geometric invariance of Bessel polynomial and possess strong capability of shape describing for 3d models. Firstly, the derivation of 3d Bessel moments are constructed and its geometric invariance proofs are given theoretically. Secondly the standardized coordinate system is calculated and the principal component analysis transform is performed to eliminate the position and scale dierences between 3d models. Thereafter, 3d models in the test sets are voxelized. Finally, 3d Bessel moments are calculated to extract rotation, scaling, and translation invariance descriptors for model retrieval. The effectiveness of the proposed method is verified on the McGill 3d shape benchmark and modelNet10 datasets. Experimental results show that the proposed method has strong robust to different simplification rates of 3d models, is invariant to rotation, scaling and translation, and performs better for model retrieval than state-of-the-art methods on test datasets.

关键词： 3d Bessel moments 3d model retrieval Invariant descriptor moments 3d Shape recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-domain Prototype Contrastive loss for Few-shot 2d Image-Based 3d model retrieval

Cross-domain Prototype Contrastive loss for Few-shot 2D Imag...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhou, Yaqian Liu, Yu Song, dan Li, Jiayu Li, Xuanya Liu, An-An Tianjin Univ Sch Microelectron Tianjin Peoples R China Inst Artificial Intelligence Hefei Comprehens Natl Sci Ctr Hefei Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Baidu Inc Beijing Peoples R China

ISBN: (纸本)9781665468916

2d image-based 3d model retrieval (IBMR) usually relies on abundant explicit supervision on 2d images, together with unlabeled 3d models to learn domain-aligned yet class-discriminative features for the retrieval task. However, collecting large-scale 2d labels is cost-effective and time-consuming. Therefore, we explore a challenging IBMR task, where only few-shot labeled 2d images are available while the rest of the 2d and 3d samples remain unlabeled. Limited annotation of 2d images further increases the difficulty of domain-aligned yet discriminative feature learning. Therefore, we propose cross-domain prototype contrastive loss (CPCL) for the few-shot IBMR task. Specifically, we capture semantic information to learn class-discriminative features in each domain by minimizing intra-domain prototype contrastive loss. Besides, we perform inter-domain transferable contrastive learning to align the features between instances and prototypes of the same class across domains. Comprehensive experiments on popular benchmarks, MI3dOR and MI3dOR-2, validate the superiority of CPCL.

关键词： 3d model retrieval self-supervised learning contrastive learning cross-domain

来源：评论

学校读者我要写书评

暂无评论

View-target relation-guided unsupervised 2d image-based 3d model retrieval via transformer

引用

MULTIMEdIA SYSTEMS 2023年第6期29卷 3891-3901页

作者： Chang, Jiacheng Zhang, Lanyong Shao, Zhuang Harbin Engn Univ Coll Intelligent Syst Sci & Engn 145 Nantong St Harbin 150001 Peoples R China Univ Warwick Warwick Mfg Grp IMC Ctr Coventry CV4 7AL W Midlands England

Unsupervised 2d image-based 3d model retrieval aims at retrieving images from the gallery of 3d models by the given 2d images. despite the encouraging progress made in this task, there are still two significant limitations: (1) feature alignment of 2d images and 3d model gallery is still difficult due to the huge gap between the two modalities. (2) The important view information in the 3d model gallery was ignored by the prior arts, which led to inaccurate results. To alleviate these limitations, inspired by the success of vision transformers (ViT) in a great variety of vision tasks, in this paper, we propose an end-to-end 3d model retrieval architecture on top of ViT, termly transformer-based 3d model retrieval network (T3dRN). In addition, to take advantage of the valuable view information of 3d models, we present an attentive module in T3dRN named shared view-guided attentive module (SVAM) to guide the learning of the alignment features. The proposed method is tested on the challenging dataset, MI3dOR-1. The extensive experimental results have proved the superiority of our proposed method to state-of-the-art methods.

关键词： 3d model retrieval Feature alignment Vision transformer View-guided attentive module

来源：评论

学校读者我要写书评

暂无评论

3d model retrieval based on interactive attention CNN and multiple features

引用

PEERJ COMPUTER SCIENCE 2023年 9卷 e1227页

作者： Gao, Xue-Yao Jia, Wen-Hui Zhang, Chun-Xiang Harbin Univ Sci & Technol Sch Comp Sci & Technol Harbin Peoples R China

3d (three-dimensional) models are widely applied in our daily life, such as mechanical manufacture, games, biochemistry, art, virtual reality, and etc. With the exponential growth of 3d models on web and in model library, there is an increasing need to retrieve the desired model accurately according to freehand sketch. Researchers are focusing on applying machine learning technology to 3d model retrieval. In this article, we combine semantic feature, shape distribution features and gist feature to retrieve 3d model based on interactive attention convolutional neural networks (CNN). The purpose is to improve the accuracy of 3d model retrieval. Firstly, 2d (two-dimensional) views are extracted from 3d model at six different angles and converted into line drawings. Secondly, interactive attention module is embedded into CNN to extract semantic features, which adds data interaction between two CNN layers. Interactive attention CNN extracts effective features from 2d views. Gist algorithm and 2d shape distribution (Sd) algorithm are used to extract global features. Thirdly, Euclidean distance is adopted to calculate the similarity of semantic feature, the similarity of gist feature and the similarity of shape distribution feature between sketch and 2d view. Then, the weighted sum of three similarities is used to compute the similarity between sketch and 2d view for retrieving 3d model. It solves the problem that low accuracy of 3d model retrieval is caused by the poor extraction of semantic features. Nearest neighbor (NN), first tier (FT), second tier (ST), F-measure (E(F)), and discounted cumulated gain (dCG) are used to evaluate the performance of 3d model retrieval. Experiments are conducted on modelNet40 and results show that the proposed method is better than others. The proposed method is feasible in 3d model retrieval.

关键词： 3d model Freehand sketch 3d model retrieval Interactive attention 2d views Euclidean distance Shape distribution feature

来源：评论

学校读者我要写书评

暂无评论

The World is Too Big to download: 3d model retrieval for World-Scale Augmented Reality 23

The World is Too Big to Download: 3D Model Retrieval for Wor...

引用

14th ACM Multimedia Systems Conference (MMSys)

作者： Tsai, Yi-Zhen Luo, James Wang, Yunshu Chen, Jiasi Univ Calif Riverside Dept Comp Sci & Engn Riverside CA 92521 USA

ISBN: (纸本)9798400701481

World-scale augmented reality (AR) is a form of AR where users move around the real world, viewing and interacting with 3d models at specific locations. However, given the geographical scale of world-scale AR, pre-fetching and storing numerous high-quality 3d models locally on the device is infeasible. For example, it would be impossible to download and store 3d ads from all the storefronts in a city onto a single device. A key challenge is thus deciding which remotely-stored 3d models should be fetched onto the AR device from an edge server, in order to render them in a timely fashion - yet with high visual quality - on the display. In this work, we propose a 3d model retrieval framework that makes intelligent decisions of which quality of 3d models to fetch, and when. The optimization decision is based on quality-compression tradeoffs, network bandwidth, and predictions of which 3d models the AR user is likely to view next. To support our framework, we collect real-world traces of AR users playing a world-scale AR game, and use this to drive our simulation and prediction modules. Our results show that the proposed framework can achieve higher visual quality of the 3d models while missing fewer display deadlines (by 20%) and wasting fewer bytes (by 10x), compared to a baseline approach of pre-fetching models within a fixed distance of the user.

关键词： Augmented reality world-scale AR 3d model retrieval

来源：评论

学校读者我要写书评

暂无评论

Source-enhanced prototypical alignment for single image 3d model retrieval

引用

COMPUTER ANIMATION ANd VIRTUAL WORLdS 2022年第3-4期33卷 e2065-e2065页

作者： Song, dan Wang, Teng Zhang, Chumeng Li, Xuanya Tong, Ruofeng Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Baidu Inc Beijing Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou Peoples R China

Single image 3d model retrieval has attracted a lot of attentions with the convenience of organizing large-scale unlabeled 3d models. Existing methods transfer the knowledge from well-annotated 2d images (i.e., source domain) to unlabeled 3d models (i.e., target domain) to improve the discriminability of 3d models and align the feature distributions of 2d images and 3d models. However, during the alignment, the feature learning target of improving the discriminability of 3d models sometimes confuses the boundaries between 2d image categories, where prior methods ignore keeping the discriminability of 2d images. Motivated by this observation, we propose a source-enhanced prototypical alignment framework to first remain the discriminability of 2d images and then guide the category-level cross-domain alignment with better image representations. Specifically, a novel separation and compactness loss is proposed for images to separate the samples from different categories and compact the samples within the same category. Then we perform prototypical alignment to make 2d image features assist in the discriminative feature learning for 3d models. We evaluate the proposed method on the commonly used cross-domain 3d model retrieval benchmarks, namely MI3dOR and MI3dOR-2, and the results demonstrate the effectiveness of the proposed method.

关键词： 3d model retrieval domain adaptation transfer learning

来源：评论

学校读者我要写书评

暂无评论

Cross-domain 3d model retrieval Based On Contrastive Learning and Label Propagation 22

Cross-Domain 3D Model Retrieval Based On Contrastive Learnin...

引用

30th ACM International Conference on Multimedia (MM)

作者： Song, dan Yang, Yue Nie, Weizhi Li, Xuanya Liu, An-An Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Hefei Comprehensice Natl Sci Ctr Inst Artificial Intelligence Hefei Peoples R China Baidu Inc Beijing Peoples R China

ISBN: (纸本)9781450392037

In this work, we aim to tackle the task of unsupervised image based 3d model retrieval, where we seek to retrieve unlabeled 3d models that are most visually similar to the 2d query image. due to the challenging modality gap between 2d images and 3d models, existing mainstream methods adopt domain-adversarial techniques to eliminate the gap, which cannot guarantee category-level alignment that is important for retrieval performance. Recent methods align the class centers of 2d images and 3d models to pay attention to the category-level alignment. However, there still exist two main issues: 1) the category-level alignment is too rough, and 2) the category prediction of unlabeled 3d models is not accurate. To overcome the first problem, we utilize contrastive learning for fine-grained category-level alignment across domains, which pulls both prototypes and samples with the same semantic information closer and pushes those with different semantic information apart. To provide reliable semantic prediction for contrastive learning and also address the second issue, we propose the consistent decision for pseudo labels of 3d models based on both the trained image classifier and label propagation. Experiments are carried out on MI3dOR and MI3dOR-2 datasets, and the results demonstrate the effectiveness of our proposed method.

关键词： 3d model retrieval domain adaptation Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Universal Cross-domain 3d model retrieval

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2021年 23卷 2721-2731页

作者： Song, dan Li, Tian-Bao Li, Wen-Hui Nie, Wei-Zhi Liu, Wu Liu, An-An Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China JD AI Res Beijing 100105 Peoples R China

Recent advances in 3d modeling technologies such as 3d scanning, reconstruction and printing produce an explosive increasing of 3d models, consequently 3d model management becomes urgent to facilitate related applications such as CAd, VR/AR and autonomous driving. However, we usually lack the labels of the recently emerging 3d models and even have no prior knowledge toward the label set relationship between new datasets and existing labeled datasets, which makes the management challenging. In this paper, a universal cross-domain 3d model retrieval framework is proposed for utilizing the labeled 2d images or 3d models to manage unlabeled 3d models with no prior knowledge about label sets. Specifically, a sample-level weighting mechanism is adopted to automatically detect the samples from the common label set for both domains. Then, both the domain-level and class-level alignments are performed for domain adaptation. Finally, the adapted features are used for 3d model retrieval. We conduct experiments on the cross-domain 3d model retrieval dataset NTU-PSB (PSB-NTU) and image-based 3d model retrieval dataset MI3dOR, and the results validate the superiority and effectiveness of the proposed method.

关键词： Three-dimensional displays Solid modeling Adaptation models Two dimensional displays Computational modeling data models Feature extraction 3d data management 3d model retrieval domain adaptation

来源：评论

学校读者我要写书评

暂无评论

3d model retrieval Based on a 3d Shape Knowledge Graph

引用

IEEE ACCESS 2020年 8卷 142632-142641页

作者： Nie, Weizhi Wang, Ya Song, dan Li, Wenhui Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

A development of 3d construction technology has led to 3d models being applied in many fields, and the number of 3d models has exploded in recent years. Thus, 3d model retrieval has become a popular topic with many proposed approaches. However, all of the methods focus on the 3d model's global structural descriptor design based on various deep learning networks and ignore the local structural information of the 3d model and the correlation of the local structures. In this paper, we propose a novel 3d model retrieval method based on a 3d shape knowledge graph. We first introduce the concept of a geometric word that can be utilized to assemble other 3d model. Second, we construct a 3d shape knowledge graph based on the geometric words, models and their relations. Additionally, we propose a novel graph embedding method to generate embeddings of nodes. Finally, an effective multiple entities' retrieval method is used to handle the 3d model retrieval problem. More specifically, the 3d shape knowledge graph retains the basic structural information and saves these as a set of triples. Any 3d model can find its geometric words in a rich enough knowledge graph. It is reasonable that our approach can solve the cross-domain model retrieval problem. Our approach focuses on the structural information of 3d model and is not restricted by the database. We evaluate the proposed method on the modelNet40 dataset for the 3d model retrieval task. Meanwhile, we also utilize the ShapeNet dataset to evaluate the performance of cross-domain retrieval task. Experimental results and comparisons with state-of-the-art methods demonstrate that our framework can achieve superior performance.

关键词： Three-dimensional displays Solid modeling Shape Task analysis data models Machine learning Biological system modeling 3d model retrieval knowledge graph graph embedding multi-view representation

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：