Dual-Graph Attention Convolution Network for 3-D Point Cloud Classification

Huang, Changqin; Jiang, Fan; Huang, Qionghao; Wang, Xizhe; Han, Zhongmei; Huang, Wen

doi:10.1109/tnnls.2022.3162301

Cited by 57 publications

(27 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such papers would be great benchmarks for further research and 3D expansion. Three-dimensional point cloud classification could also be considered, for example, [ 87 ].…”

Section: Machine Learning For 3d Indoor Positioningmentioning

confidence: 99%

A Survey of 3D Indoor Localization Systems and Technologies

Sesyuk

Ioannou

Raspopoulos

2022

Sensors

View full text Add to dashboard Cite

Indoor localization has recently and significantly attracted the interest of the research community mainly due to the fact that Global Navigation Satellite Systems (GNSSs) typically fail in indoor environments. In the last couple of decades, there have been several works reported in the literature that attempt to tackle the indoor localization problem. However, most of this work is focused solely on two-dimensional (2D) localization, while very few papers consider three dimensions (3D). There is also a noticeable lack of survey papers focusing on 3D indoor localization; hence, in this paper, we aim to carry out a survey and provide a detailed critical review of the current state of the art concerning 3D indoor localization including geometric approaches such as angle of arrival (AoA), time of arrival (ToA), time difference of arrival (TDoA), fingerprinting approaches based on Received Signal Strength (RSS), Channel State Information (CSI), Magnetic Field (MF) and Fine Time Measurement (FTM), as well as fusion-based and hybrid-positioning techniques. We provide a variety of technologies, with a focus on wireless technologies that may be utilized for 3D indoor localization such as WiFi, Bluetooth, UWB, mmWave, visible light and sound-based technologies. We critically analyze the advantages and disadvantages of each approach/technology in 3D localization.

show abstract

“…Such papers would be great benchmarks for further research and 3D expansion. Three-dimensional point cloud classification could also be considered, for example, [ 87 ].…”

Section: Machine Learning For 3d Indoor Positioningmentioning

confidence: 99%

A Survey of 3D Indoor Localization Systems and Technologies

Sesyuk

Ioannou

Raspopoulos

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In addition to graph-convolution-based methods, another line of work aims to improve graph attention neural networks for point cloud analysis [233], [234], [235], [236], where the attention weights are computed from both neighbors' positions and learnable features. Besides, Graph-RNN is explored in [237] to jointly consider relations between both spatially and temporally neighboring points for point cloud sequence analysis.…”

Section: Point Cloud Representationmentioning

confidence: 99%

A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective

Chen¹,

Wu²,

Dai³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (e.g., social network analysis and recommender systems), computer vision (e.g., object detection and point cloud learning), and natural language processing (e.g., relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, i.e., 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.

show abstract

“…The GANs have been widely used in image generation [7], [24], [29], [43]- [45], image translation [46], [47], and image synthesis [12], [13]. Recent literature regarding deep learning approaches [48]- [54] focuses more on face recognition and classification problems than classical methods [55]- [57]. These approaches can also be used for sketch-photo recognition problems.…”

Section: Related Workmentioning

confidence: 99%

Face Recognition via Multi-Level 3D-GAN Colorization

et al. 2022

View full text Add to dashboard Cite

Rapid development in sketch-to-image translation methods boosts the investigation procedure in law enforcement agencies. But, the large modality gap between manually generated sketches makes this task challenging.Generative adversarial network (GAN) and encoder-decoder approach are usually incorporated to accomplish sketchto-image generation with promising results. This paper targets the sketch-to-image translation with heterogeneous face angles and lighting effects using a multi-level conditional generative adversarial network. The proposed multilevel cGAN work in four different phases. Three independent cGANs' networks are incorporated separately into each stage, followed by a CNN classifier. The Adam stochastic gradient descent mechanism was used for training with a learning rate of 0.0002 and momentum estimates β1 and β2 as 0.5 and 0.999, respectively. The multi-level 3Dconvolutional architecture help to preserve spatial facial attributes and pixel-level details. The 3D convolution and deconvolution guide the G1, G2 and G3 to use additional features and attributes for encoding and decoding. This helps to preserve the direction, postures of targeted image attributes and special relationships among the whole image's features. The proposed framework process the 3D-Convolution and 3D-Deconvolution using vectorization. This process takes the same time as 2D convolution but extracts more features and facial attributes. We used pre-trained ResNet-50, ResNet-101, and Mobile-Net to classify generated high-resolution images from sketches. We have also developed, and state-of-the-art Pakistani Politicians Face-sketch Dataset (PPFD) for experimental purposes. Result reveals that the proposed cGAN model's framework outperforms with respect to Accuracy, Structural similarity index measure (SSIM), Signal to noise ratio (SNR), and Peak signal-to-noise ratio (PSNR).

show abstract

Dual-Graph Attention Convolution Network for 3-D Point Cloud Classification

Cited by 57 publications

References 48 publications

A Survey of 3D Indoor Localization Systems and Technologies

A Survey of 3D Indoor Localization Systems and Technologies

A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective

Face Recognition via Multi-Level 3D-GAN Colorization

Contact Info

Product

Resources

About