相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Jaehyun Park et al.
Summary: This paper introduces a fast voxel-based semantic segmentation model, using Point Convolution and 3D Sparse Convolution for feature extraction and propagation, to improve the real-time performance of recognizing the driving environment.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Jie Li et al.
Summary: With the rapid development of 3D vision technology and increasing application of 3D objects, there is a need for better recognition methods. Existing view-based methods lack sufficient information interaction between different views. Inspired by vision transformer (ViT), a hybrid network is proposed that combines convolutional neural networks (CNN) and transformer to improve 3D object recognition performance. Experiment results show that the proposed multi-view convolutional vision transformer (MVCVT) has competitive performance compared to state-of-the-art methods on benchmark datasets.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2023)
Article
Computer Science, Artificial Intelligence
Saifullahi Aminu Bello et al.
Summary: This article introduces a deep learning model called PDConvNet for handling rigid transformation on 3D point clouds. By extracting invariant features from the point set, the model is able to maintain invariance during rigid transformations and achieve competitive performance on point cloud classification and segmentation tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Chenke Yue et al.
Summary: This paper proposes a new method for processing point cloud data called Dynamic Region Graph Convolution. By constructing dynamic graphs and selecting receptive fields, point cloud data can be effectively processed, improving recognition accuracy and robustness.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Shi Qiu et al.
Summary: This paper proposes an improved network model that addresses the challenges in point cloud analysis. By enriching geometric information in low-level space and learning geometric context in high-level feature space, the network captures comprehensive local features of point clouds. An attention module is also used to avoid redundancy. The performance on various datasets demonstrates the superiority and applicability of the network.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Engineering, Electrical & Electronic
Xue Wang et al.
Summary: This article proposes a decoupling network-based method for infrared and visible image fusion, which effectively retains the texture details and luminance information of the source images while preserving the high-contrast regions. Extensive experiments demonstrate that the proposed method generates fused images with saliency objects and clear details, outperforming other state-of-the-art methods.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Qi Liu et al.
Summary: The article introduces a novel deep learning-based no reference point cloud quality assessment method, PQA-Net, with promising applications in immersive communication and outstanding performance in experiments.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Automation & Control Systems
A. A. M. Muzahid et al.
Summary: In this paper, a method for 3D object recognition based on principal curvature directions, named CurveNet, is proposed, which effectively extracts geometric features of 3D objects and combines multitask learning for improved classification performance. Experimental results show that the method is competitive in the 3D object recognition task.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kirill Mazur et al.
Summary: The new versatile building block combines spatial transformers, multi-view convolutional networks, and dense convolution layers to achieve state-of-the-art performance in point cloud processing tasks. The block operates via multiple parallel heads for feature representation and information propagation, showcasing its versatility in diverse tasks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Article
Computer Science, Software Engineering
Meng-Hao Guo et al.
Summary: This paper introduces a novel framework named Point Cloud Transformer (PCT) for point cloud learning, based on Transformer and enhanced by farthest point sampling and nearest neighbor search for better capturing local context. Extensive experiments demonstrate that the PCT achieves state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.
COMPUTATIONAL VISUAL MEDIA
(2021)
Article
Computer Science, Software Engineering
Yue Wang et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Computer Science, Artificial Intelligence
Kaleem Siddiqi et al.
MACHINE VISION AND APPLICATIONS
(2008)
