Learning Discriminative and Generative Shape Embeddings for Three-Dimensional Shape Retrieval

Xu, Cheng; Leng, Biao; Chen, Bin; Zhang, Cheng; Xiaocheng, Zhou

doi:10.1109/tmm.2019.2957933

Cited by 8 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because in the Bragg equation, the distance between the crystal planes a is a harsh limiting condition. It only represents the distance between the two crystal planes, but it does not mean that the two ends of a will fall on the lattice points of the two crystal planes [10]. Bragg equation is an important equation in crystal chemistry.…”

Section: Significance Of Bragg Equationmentioning

confidence: 99%

Retrieval and Characteristic Analysis of Multimedia Tester Based on Bragg Equation

Gao

Babaker

2022

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In order to solve the problem of Bragg equation, a research on retrieval and feature of multimedia testing machine is proposed. Firstly, this paper investigates the various stages of multimedia retrieval system and some mainstream multimedia retrieval algorithms, in order to cover all aspects of relevant algorithms. Secondly, on the basis of investigation, eight representative algorithms are selected. These algorithms cover three stages of multimedia retrieval system, including feature extraction stage, feature matching stage and geometric verification stage. Based on the above observed characteristics, finally, some relevant suggestions on architecture design and system optimization are put forward, including the design of single node processor, the design in parallel environment and the suggestions for simulation and evaluation using this test set.

show abstract

Section: Significance Of Bragg Equationmentioning

confidence: 99%

Retrieval and Characteristic Analysis of Multimedia Tester Based on Bragg Equation

Gao

Babaker

2022

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

“…Zhou et al proposed the multi-view saliency guided deep neural network (MVSG-DNN) which contains three modules to capture and extract the features of individual views to compile 3D object descriptors for 3D object retrieval and classification [19]. Xu et al used a LSTM-based network to recurrently aggregate the 3D objects shape embedding from an image sequence and estimate images of unseen viewpoints, aiming at the fusion of multiple views' features [26]. Huang et al devised a view mixture model (VMM) to decompose the multiple views into a few latent views for the descriptor construction [27].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data

Jiang¹,

Lu²,

Ouyang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training. By contrast, unsupervised learning of point cloud data has received much less attention to date. In this paper, we propose a simple yet effective approach for unsupervised point cloud learning. In particular, we identify a very useful transformation which generates a good contrastive version of an original point cloud. They make up a pair. After going through a shared encoder and a shared head network, the consistency between the output representations are maximized with introducing two variants of contrastive losses to respectively facilitate downstream classification and segmentation. To demonstrate the efficacy of our method, we conduct experiments on three downstream tasks which are 3D object classification (on ModelNet40 and ModelNet10), shape part segmentation (on ShapeNet Part dataset) as well as scene segmentation (on S3DIS). Comprehensive results show that our unsupervised contrastive representation learning enables impressive outcomes in object classification and semantic segmentation. It generally outperforms current unsupervised methods, and even achieves comparable performance to supervised methods. Our source codes will be made publicly available.

show abstract

“…Latest works [1]- [4] show the potential of directly consuming points, and they do not need to convert the point clouds into other forms, such as voxel form [5]- [8]. Many works have explored the learning of single point cloud on 3D object retrieval [9]- [11], classification [1], [2], and segmentation [12]- [14]. There are a few pieces of research on the learning of multi-frame point cloud, and there remain some challenges.…”

Section: Introductionmentioning

confidence: 99%

Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences

Wang,

Chen,

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

Recently, learning based methods for the robot perception from the image or video have much developed, but deep learning methods for dynamic 3D point cloud sequences are underexplored. With the widespread application of 3D sensors such as LiDAR and depth camera, efficient and accurate perception of the 3D environment from 3D sequence data is pivotal to autonomous driving and service robots. An Anchor-based Spatial-Temporal Attention Convolution operation (ASTAConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on spatial-temporal attention mechanism. Then, anchor-based sparse 3D convolution is adopted to aggregate the features of these anchors to the core points. The proposed method makes better use of the structured information within the local region, and learn spatial-temporal embedding features from dynamic 3D point cloud sequences. Then Anchor-based Spatial-Temporal Attention Convolutional Neural Networks (ASTACNNs) are proposed for classification and segmentation tasks and are evaluated on action recognition and semantic segmentation tasks. The experimental results on MSRAction3D and Synthia datasets demonstrate that the higher accuracy can be achieved than the previous state-of-the-art method by our novel strategy of multi-frame fusion.

show abstract

Learning Discriminative and Generative Shape Embeddings for Three-Dimensional Shape Retrieval

Cited by 8 publications

References 36 publications

Retrieval and Characteristic Analysis of Multimedia Tester Based on Bragg Equation

Retrieval and Characteristic Analysis of Multimedia Tester Based on Bragg Equation

Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data

Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences

Contact Info

Product

Resources

About