检索结果-内蒙古大学图书馆

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Hou, Wentao diao, Zhenyu Peng, Jingliang Univ Jinan Shandong Prov Key Lab Network Based Intelligent C Jinan 250022 Peoples R China Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China

ISBN: (纸本)9789819785070;9789819785087

sketch-based 3d shape retrieval (SBSR) is to find from a repository the 3d shapes most similar to a user-drawn sketch. There are two key challenges for this task. Firstly, sketch and 3d shape are different modalities of object representation and there exists a domain gap between them. Secondly, sketches tend to be noisy since all sketchers are not expected to have a consistently good level of drawing skills, which may cause overfitting. In this work, we propose approaches to effectively overcome these challenges. For the cross-domain feature alignment, we employ cross-modal contrastive learning that avoids the inefficiency and instability issues of triplet-based training as usually adopted by the existing SBSR methods. Further, in order to mitigate the negative impact of noisy sketch data on network learning, we employ a relative Mahalanobis distance based metric to measure sketch sample difficulty and introduce difficulty-aware uncertainty regularization into the loss function. Experiments conducted on the SHREC'13 and SHREC'14 datasets demonstrate the state-of-the-art performance of our proposed model and the effectiveness of our proposed algorithmic components.

关键词： sketch-based 3d shape retrieval Constrastive learning Sample difficulty Uncertainty regularization

来源：评论

学校读者我要写书评

暂无评论

dKd2L: dual Knowledge distillation dynamic Learning for sketch-based 3d shape retrieval

DKD2L: Dual Knowledge Distillation Dynamic Learning for sket...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Su, Yawen Bai, Jing Lin, Gan School of Computer Science and Engineering North Minzu University Yinchuan China The Key Laboratory of Images & Graphics Intelligent Processing of State Ethnic Affairs Commission China

ISBN: (纸本)9798350368741

sketch-based 3d shape retrieval has become a prominent area of research in computer vision, confronting challenges related to the inherent diversity and abstraction of sketches, as well as inter-domain discrepancies. This paper introduces a novel approach called dual Knowledge distillation dynamic Learning (dKd2L) aimed at enhancing the extraction of spatio-temporal features for sketch-based 3d shape retrieval. We develop a temporal feature extraction network to effectively capture the dynamic temporal characteristics of sketches and improve retrieval efficiency through temporal knowledge distillation. Additionally, to tackle intra-class variation and inter-class imbalance, we apply semantic knowledge distillation, enabling the 3d shape network to guide the sketch network in capturing common semantic information. This approach facilitates precise cross-modal alignment and enhances retrieval accuracy. Extensive experiments on two benchmark datasets demonstrate that dKd2L surpasses existing state-of-the-art methods. © 2025 IEEE.

关键词： 3d shape retrieval Knowledge distillation sketch-based 3d shape retrieval Temporal Feature

来源：评论

学校读者我要写书评

暂无评论

SKd-SBSR: Structural Knowledge distillation for sketch-based 3d shape retrieval

引用

KNOWLEdGE-based SYSTEMS 2025年 310卷

作者： Su, Yawen Li, Wenjing Bai, Jing Lin, Gan North Minzu Univ Sch Comp Sci & Engn Yinchuan 750021 Peoples R China Key Lab Images & Graph Intelligent Proc State Ethn Yinchuan 750021 Peoples R China

sketch-based 3d shape retrieval (SBSR) is a complex cross-modal matching problem, primarily due to the heterogeneous distribution of cross-modal data and the sparse, diverse nature of sketches. A crucial yet often overlooked characteristic of sketches is their consistent internal structural features, despite being human- drawn and varied. We argue that an effective SBSR model can explicitly consider this structural consistency, emphasizing the extraction of rich, multi-grained features from sketches. Moreover, a successful transfer of this structural information to conventional geometric features is essential. To address these challenges, we propose a novel method called Structural Knowledge distillation for sketch-based 3d shape retrieval (SKd-SBSR), which explicitly considers the structural coherence of sketches. Key innovations include a dual-branch sketch- 3d shape feature extraction Network (dualNet) with a Progressive Loss (PLoss) that incrementally adapts the strength of loss constraints to ensure geometric feature consistency and flexibility. We also introduce a Structural Feature extraction Network (SFNet) equipped with a Multi-Grained Structural Feature (MGSF) encoder, which captures rich structural features through graph transformer and feature fusion operations. To fully utilize both structural and geometric features, we propose a Structural Feature Knowledge distillation (SFKd) module that effectively transfers structural knowledge, thereby enhancing the feature representation of dualNet and achieving robust retrieval. Comprehensive experiments on the SHREC'13, SHREC'14, and Part-SHREC'14 datasets demonstrate that SKd-SBSR achieves state-of-the-art performance in SBSR tasks.

关键词： sketch-based 3d shape retrieval Structural consistency Graph transformer sketch domain enhancement Knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2018年第7期27卷 3374-3386页

作者： dai, Guoxian Xie, Jin Fang, Yi New York Univ NYU Multimedia & Visual Comp Lab Abu Dhabi 129188 U Arab Emirates New York Univ Dept Elect & Comp Engn Abu Dhabi 129188 U Arab Emirates NYU Tandon Sch Engn Dept Elect & Comp Engn Brooklyn NY 11201 USA

How to effectively retrieve desired 3d models with simple queries is a long-standing problem in computer vision community. The model-based approach is quite straightforward but nontrivial, since people could not always have the desired 3d query model available by side. Recently, large amounts of wide-screen electronic devices are prevail in our daily lives, which makes the sketch-based 3d shape retrieval a promising candidate due to its simpleness and efficiency. The main challenge of sketch-based approach is the huge modality gap between sketch and 3d shape. In this paper, we proposed a novel deep correlated holistic metric learning (dCHML) method to mitigate the discrepancy between sketch and 3d shape domains. The proposed dCHML trains two distinct deep neural networks (one for each domain) jointly, which learns two deep nonlinear transformations to map features from both domains into a new feature space. The proposed loss, including discriminative loss and correlation loss, aims to increase the discrimination of features within each domain as well as the correlation between different domains. In the new feature space, the discriminative loss minimizes the intra-class distance of the deep transformed features and maximizes the inter-class distance of the deep transformed features to a large margin within each domain, while the correlation loss focused on mitigating the distribution discrepancy across different domains. different from existing deep metric learning methods only with loss at the output layer, our proposed dCHML is trained with loss at both hidden layer and output layer to further improve the performance by encouraging features in the hidden layer also with desired properties. Our proposed method is evaluated on three benchmarks, including 3d shape retrieval Contest 2013, 2014, and 2016 benchmarks, and the experimental results demonstrate the superiority of our proposed method over the state-of-the-art methods.

关键词： sketch-based 3d shape retrieval deep correlated holistic metric learning discrepancy across different domains mitigate

来源：评论

学校读者我要写书评

暂无评论

deep Cross-Modality Adaptation via Semantics Preserving Adversarial Learning for sketch-based 3d shape retrieval 15th

Deep Cross-Modality Adaptation via Semantics Preserving Adve...

引用

15th European Conference on Computer Vision (ECCV)

作者： Chen, Jiaxin Fang, Yi New York Univ Abu Dhabi NYU Multimedia & Visual Comp Lab Dept Elect & Comp Engn Abu Dhabi U Arab Emirates NYU Tandon Sch Engn Dept Elect & Comp Engn New York NY 10016 USA

ISBN: (纸本)9783030012618;9783030012601

due to the large cross-modality discrepancy between 2d sketches and 3d shapes, retrieving 3d shapes by sketches is a significantly challenging task. To address this problem, we propose a novel framework to learn a discriminative deep cross-modality adaptation model in this paper. Specifically, we first separately adopt two metric networks, following two deep convolutional neural networks (CNNs), to learn modality-specific discriminative features based on an importance-aware metric learning method. Subsequently, we explicitly introduce a cross-modality transformation network to compensate for the divergence between two modalities, which can transfer features of 2d sketches to the feature space of 3d shapes. We develop an adversarial learning based method to train the transformation model, by simultaneously enhancing the holistic correlations between data distributions of two modalities, and mitigating the local semantic divergences through minimizing a cross-modality mean discrepancy term. Experimental results on the SHREC 2013 and SHREC 2014 datasets clearly show the superior retrieval performance of our proposed model, compared to the state-of-the-art approaches.

关键词： sketch-based 3d shape retrieval Cross-modality transformation Adversarial learning Importance-aware metric learning

来源：评论

学校读者我要写书评

暂无评论

HdA2L: Hierarchical domain-Augmented Adaptive Learning for sketch-based 3d shape retrieval

引用

KNOWLEdGE-based SYSTEMS 2023年第1期264卷

作者： Bai, Shaojin Bai, Jing North Minzu Univ Sch Comp Sci & Engn Yinchuan 750021 Peoples R China Key Lab Images & Graph Intelligent Proc State Ethn Yinchuan 750021 Peoples R China

The sketch-based 3d shape retrieval has been an active but challenging task for several decades. In this paper, we deeply analyze the challenges and propose a novel Hierarchical domain-Augmented Adaptive Learning (HdA2L) for sketch-based 3d shape retrieval. The first notable challenge is the vast cross-modality discrepancies between sketches and 3d shapes. To this issue, the existing methods restrict the consistency of the final features by establishing a shared cross-domain loss but ignore the feature extraction process, resulting in a limited effect. We argue that the mutual information of the samples from the same class but different domains can provide an important cue to enhance common features captured in the feature extraction process. Thus, we design an Inter-domain Augmented Network (Inter-dAN) by employing inter-domain feature correlation learning to capture cross-domain mutual information to learn augmented common global features for both sketches and 3d shapes. Another challenge is that the input sketch is various: it may be particularly abstract and contains only the overall outline of the target model, or it may be too sketchy and only contains some salient local regions of the target model. Though existing methods have demonstrated their capability to capture overall features, they always ignore the learning of local discriminative features and fail to adapt to the various changes of input sketches. To address this issue, we design an Intra-domain Augmented Network (Intra-dAN) for sketches and 3d shapes, respectively, which learns augmented local discrim-inative features by adopting cascading cross-layer bilinear pooling operations. In addition, we design a Source-Agnostic Adversarial Network (SAAN) to accomplish the adaptive hierarchical domain features fusion, which forces the network to adaptively focus on more discriminative information from global features and local features and further adapt the diversity of the input sketches. The experiments o

关键词： sketch-based 3d shape retrieval Inter-domain augmented Intra-domain augmented Adaptive adversarial learning Hierarchical learning

来源：评论

学校读者我要写书评

暂无评论

deep point-to-subspace metric learning for sketch-based 3d shape retrieval

引用

PATTERN RECOGNITION 2019年 96卷 106981-000页

作者： Lei, Yinjie Zhou, Ziqin Zhang, Pingping Guo, Yulan Ma, Zijun Liu, Lingqiao Sichuan Univ Coll Elect & Informat Engn Chengdu Sichuan Peoples R China Dalian Univ Technol Sch Informat & Commun Engn Dalian Peoples R China Sun Yat Sen Univ Sch Elect & Commun Engn Guangzhou Guangdong Peoples R China Natl Univ Def Technol Coll Elect Sci & Engn Changsha Hunan Peoples R China Univ Adelaide Sch Comp Sci Adelaide SA Australia

One key issue in managing a large scale 3d shape dataset is to identify an effective way to retrieve a shape-of-interest. The sketch-based query, which enjoys the flexibility in representing the user's intention, has received growing interests in recent years due to the popularization of the touchscreen technology. Essentially, the sketch depicts an abstraction of a shape in a certain view while the shape contains the full 3d information. Matching between them is a cross-modality retrieval problem, and the state-of-the-art solution is to project the sketch and the 3d shape into a common space with which the cross-modality similarity can be calculated by the feature similarity/distance within. However, for a given query, only part of the viewpoints of the 3d shape is representative. Thus, blindly projecting a 3d shape into a feature vector without considering what is the query will inevitably bring query-unrepresentative information. To handle this issue, in this work we propose a deep Point-to-Subspace Metric Learning (dPSML) framework to project a sketch into a feature vector and a 3d shape into a subspace spanned by a few selected basis feature vectors. The similarity between them is defined as the distance between the query feature vector and its closest point in the subspace by solving an optimization problem on the fly. Note that, the closest point is query-adaptive and can reflect the viewpoint information that is representative to the given query. To efficiently learn such a deep model, we formulate it as a classification problem with a special classifier design. To reduce the redundancy of 3d shapes, we also introduce a Representative-View Selection (RVS) module to select the most representative views of a 3d shape. By conducting extensive experiments on various datasets, we show that the proposed method can achieve superior performance over its competitive baseline methods and attain the state-of-the-art performance. (C) 2019 Elsevier Ltd. All rights reserv

关键词： sketch-based 3d shape retrieval Cross-modality discrepancy Representative-view selection Point-to-subspace distance

来源：评论

学校读者我要写书评

暂无评论

JFLN: Joint Feature Learning Network for 2d sketch based 3d shape retrieval

引用

JOURNAL OF VISUAL COMMUNICATION ANd IMAGE REPRESENTATION 2022年 89卷

作者： Zhao, Yue Liang, Qi Ma, Ruixin Nie, Weizhi Su, Yuting Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Tianjin Nav Instrument Res Inst Tianjin 300131 Peoples R China Dalian Maritime Univ Key Lab Marine Simulat & Control Dalian 116026 Peoples R China MOT Tianjin Res Inst Water Transport Engn Tianjin 300456 Peoples R China

Cross-modal retrieval attracts much research attention due to its wide applications in numerous search systems. sketch based 3d shape retrieval is a typical challenging cross-modal retrieval task for the huge divergence between sketch modality and 3d shape view modality. Existing approaches project the sketches and shapes into a common space for feature update and data alignment. However, these methods contain several disadvantages: Firstly, the majority approaches ignore the modality-shared information for divergence compensation in descriptor generation process. Secondly, traditional fusion method of multi-view features introduces much redundancy, which decreases the discrimination of shape descriptors. Finally, most approaches only focus on the cross-modal alignment, which omits the modality-specific data relevance. To address these limitations, we propose a Joint Feature Learning Network (JFLN). Firstly, we design a novel modality-shared feature extraction network to exploit both modality-specific characteristics and modality-shared information for descriptor generation. Subsequently, we introduce a hierarchical view attention module to gradually focus on the effective information for multiview feature updating and aggregation. Finally, we propose a novel cross-modal feature learning network, which can simultaneously contribute to modality-specific data distribution and cross-modal data alignment. We conduct exhaustive experiments on three public databases. The experimental results validate the superiority of the proposed method. Full Codes are available at https: //***/dlmuyy/JFLN.

关键词： sketch-based 3d shape retrieval Attention mechanism Cross-modal retrieval

来源：评论

学校读者我要写书评

暂无评论

retrieval-Specific View Learning for sketch-to-shape retrieval

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2025年 27卷 768-779页

作者： Yuan, Shuaihang Wen, Congcong Liu, Yu-Shen Fang, Yi New York Univ NYUAD Ctr Artificial Intelligence & Robot Abu Dhabi 100121126 U Arab Emirates NYU NYU Multimedia & Visual Comp Lab New York NY 10012 USA New York Univ Abu Dhabi 100121126 U Arab Emirates Tsinghua Univ Sch Software Beijing 100084 Peoples R China

sketch-based 3d shape retrieval (SBSR) can be approached by learning domain-invariant descriptors or ranking metrics from sketches and 2d view images of 3d shapes rendered through numerous viewpoints. However, determining the most appropriate viewpoints that convey discriminative geometric features to benefit the task of SBSR became an essential yet not fully explored area. Existing works extract 3d features from multi-view images observed through pre-defined viewpoints to match 2d sketches. Those methods, however, fail to dynamically select viewpoints by considering the SBSR task. In this work, we introduce a fully differentiable viewpoint learning paradigm driven by the downstream SBSR task, which supports the task-aware and sketch-dependent dynamic viewpoint determination process. We naturally integrate this task-specific and sketch-dependent viewpoint learning process into a meta-learning framework to develop a novel dynamic Viewer (dV) module for category-level SBSR. dV module comprises a Meta View Learner (MVL) block and a View Generator (VG) block. Specifically, as the first part of the dV module, the MVL block learns to initiate the necessary network parameters of the VG block. Then, the VG block that serves as the second part learns the best viewpoints to render 2d images. To learn the optimal viewpoints for category-level SBSR, we further introduce a view mining loss that aims to maximize the similarity of feature-level information among rendered 2d views and the query sketch. Further, we adopt a variational autoencoder (VAE) to retrieve 3d shapes by setting the newly rendered images and query sketch as inputs. Comprehensive experimental results on popular SBSR datasets demonstrate that our proposed category-level SBSR framework have achieved state-of-the-art performance for category-level SBSR task. Furthermore, our approach can be easily adapted to address instance-level SBSR task with promising results.

关键词： sketch-based 3d shape retrieval Optimal 2d views task-specific viewpoint learning sketch-based 3d shape retrieval task-specific viewpoint learning

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：