检索结果-内蒙古大学图书馆

10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

作者： Zhou, Shenglong Xiong, Zhiwei Chen, Chang Chen, Xuejin Liu, dong Zhang, Yueyi Zha, Zheng-Jun Wu, Feng Univ Sci & Technol China Hefei Peoples R China

ISBN: (纸本)9783030322397;9783030322380

We propose an unsupervised deep learning method for serial electron microscopy (EM) image registration with fast speed and high accuracy. Current registration methods are time consuming in practice due to the iterative optimization procedure. We model the registration process as a parametric function in the form of convolutional neural networks, and optimize its parameters based on features extracted from training serial EM images in a training set. Given a new series of EM images, the deformation field of each serial image can be rapidly generated through the learned function. Specifically, we adopt a spatial transformer layer to reconstruct features in the subject image from the reference ones while constraining smoothness on the deformation field. Moreover, for the first time, we introduce the 3d convolution layer to learn the relationship between several adjacent images, which effectively reduces error accumulation in serial EM image registration. Experiments on two popular EM datasets, Cremi and FIB25, demonstrate our method can operate in an unprecedented speed while providing competitive registration accuracy compared with state-of-the-art methods, including learning-based ones.

关键词： Unsupervised learning Serial-section EM Image registration 3d convolution

来源：评论

学校读者我要写书评

暂无评论

POSE GUIdEd PERSON IMAGE GENERATION BASEd ON POSE SKELETON SEQUENCE ANd 3d convolution

POSE GUIDED PERSON IMAGE GENERATION BASED ON POSE SKELETON S...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Zhao, Wenbin Xie, Qing Ma, Yanchun Liu, Yongjian Xiong, Shengwu Wuhan Univ Technol Sch Comp Sci & Technol Wuhan Peoples R China

ISBN: (纸本)9781728163956

This paper proposes a novel approach for pose transfer, which aims at transferring the pose of a given person to a target pose. Unlike previous works directly simulating the target pose, we emphasize the pose geometric constraint in our approach to tackle this task. To capture the geometric constraints among the condition pose and target pose, we generate a sequence of different intermediate pose skeleton. Moreover, we introduced the 3d convolution into the generator of our Generative Adversarial Network (GAN) in order to learn spatiotemporal features from the generated pose skeleton sequence. The final target pose will be estimated and refined by a pose transfer block and a series of residual blocks based on the spatiotemporal features. Compared with the existing works, our generated person pose images achieved better performance in terms of Inception Score and Structure Similarity. Extensive experiments on dataset Market-1501 demonstrate the effectiveness of the pose skeleton sequence on pose transfer.

关键词： Pose transfer Pose skeleton sequence 3d convolution GAN

来源：评论

学校读者我要写书评

暂无评论

A NEW 3d convolution NETWORK FOR HYPERSPECTRAL UNMIXING

A NEW 3D CONVOLUTION NETWORK FOR HYPERSPECTRAL UNMIXING

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Tao, X. Paoletti, M. E. Han, L. Wu, Z. Jimenez, L. I. Haut, J. M. Ren, P. Plaza, J. Plaza, A. Univ Extremadura Dept Technol Comp & Commun Badajoz Spain Univ Complutense Madrid Dept Architecture Comp & Automat Madrid Spain China Univ Petr East China Coll Informat & Control Engn Dongying Peoples R China

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

Hyperspectral unmixing aims at extracting pure spectral signatures and estimating their corresponding abundances at each pixel. Traditional unmixing algorithms consider end-member extraction and abundance estimation as two separate steps, and the completion of abundance estimation requires results from other endmember extraction algorithms. Considering that convolutional neural networks (CNNs) have powerful learning and data fitting capabilities, some techniques based on deep learning (dL) have been proposed in the literature. Most of them only utilize spectral information and neglect spatial information. In addition, existing unmixing methods based on dL usually extract the weight and output of a specific activation layer as endmembers and abundances, respectively. In our work, we exploit 3d convolution to propose a new 3d convolution unmixing network (3dCUN) for hyperspectral unmixing. Two types of real data, i.e., Samson and Jasper, are used to evaluate the performance of our proposed 3dCUN in endmember extraction and abundance estimation. The experimental results reflect that our proposed 3dCUN gets accurate results in estimating endmembers and abundances.

关键词： Hyperspectral unmixing convolutional neural network 3d convolution

来源：评论

学校读者我要写书评

暂无评论

deep Video Compression Based on 3d convolution Artifacts Removal and Attention Compression Module 1

引用

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Liu, Zhichen Luo, Jianping Shenzhen Univ Coll Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen Peoples R China

ISBN: (数字)9783031442049

ISBN: (纸本)9783031442032;9783031442049

Most research of video compression focuses on how to effectively extract the information between frames and use this information for the subsequent reconstruction. Previous algorithms used 2d convolution to extract information between adjacent frames, but 2d convolution is insufficient in spatio-temporal extraction ability, so we consider using a 3d convolution network to remove artifacts caused by motion compensation. In order to further improve the compression performance, we put the 3d convolution network and the residual compression network into the feature space to reduce the errors caused by inaccurate pixel-level operations. In addition, we also propose a motion compression network based on attention module, so that the network can pay more attention to the complex area of the image. Experimental results show that our model achieves the same or even better performance than other end-to-end video compression models in PSNR and MS-SSIM, even though our method has a much smaller number of parameters.

关键词： 3d convolution feature space attention module

来源：评论

学校读者我要写书评

暂无评论

Fusion Information Attention Mechanism Based on 3d convolution 2

Fusion Information Attention Mechanism Based on 3D Convoluti...

引用

2nd International Conference on Intelligent Communication and Networking, ICN 2024

作者： Tian, Yao Yong, Xu Hao, Huang Hongtao, Yan Yue, Ma Zehua, deng Aerospace Technology Institute of CARDC South section of Second Ring Road Si Chuan Mian Yang China

ISBN: (纸本)9798331519162

The image quality captured in scenarios involving fast motion, low light, and ultra-long distances tends to be poor, resulting in insufficient information richness and making it difficult to utilize the effective information within the image. This causes the network to struggle to focus on areas with enough useful information. To address this issue, this paper proposes an information fusion attention mechanism based on 3d convolution. Firstly, 3d convolution is used to fuse channel and spatial information, facilitating interaction between them and increasing the richness of the information. Next, AdaptiveAvgPool3d is employed to encode attention for both spatial and channel dimensions separately. Finally, the attention weights for spatial and channel dimensions are integrated through fusion. The attention mechanism proposed in this paper serves as a plug-and-play module that can be combined with any backbone network. Experimental results demonstrate its advanced performance in object detection and classification tasks. © 2024 IEEE.

关键词： 3d convolution attention deep learning fusion information

来源：评论

学校读者我要写书评

暂无评论

A review of video action recognition based on 3d convolution

引用

COMPUTERS & ELECTRICAL ENGINEERING 2023年第1期108卷

作者： Huang, Xiankai Cai, Zhibin Beijing Technol & Business Univ Beijing 100048 Peoples R China

Video action recognition is one of the topics for video understanding. Over the past decade, video action recognition has made great progress due to the emergence of deep learning, especially, the application of 3d convolution, which further improves the accuracy of recognition. However, three challenges remain: difficulty in capturing long video features, high computational costs, and difficulty in comparing methods due to different benchmarks. Therefore, in view of the above three challenges, this paper summarizes and analyzes existing video action recognition methods based on 3d convolution to help new researchers understand this field. Our contributions include 3 parts. Firstly, we introduce the classical video action recognition methods based on 3d convolution and point out two problems of the methods. Then, we summarize the existing improved methods based on 3d convolution and the popular datasets and compare and analyze the experimental results of these methods on the benchmark. Finally, we discuss current chal-lenges for video action recognition and analyze future development trends.

关键词： Computer vision Video action recognition 3d convolution deep learning

来源：评论

学校读者我要写书评

暂无评论

Multiband seizure type classification based on 3d convolution with attention mechanisms

引用

COMPUTERS IN BIOLOGY ANd MEdICINE 2023年 166卷 107517-107517页

作者： Huang, Hui Chen, Peiyu Wen, Jianfeng Lu, Xuzhe Zhang, Nan Wenzhou Univ Coll Comp Sci & Artificial Intelligence Wenzhou 325035 Peoples R China

Electroencephalogram (EEG) signal contains important information about abnormal brain activity, which has become an important basis for epilepsy diagnosis. Recently, epilepsy EEG signal classification methods mainly extract features from the perspective of a single domain, which cannot effectively utilize the spatial domain information in EEG signals. The redundant information in EEG signals will affect the learning features with the increase of convolution layer and multi-domain features, resulting in inefficient learning and a lack of distinguishing features. To tackle these issues, we propose an end-to-end 3d convolutional multiband seizure-type classification model based on attention mechanisms. Specifically, to process preprocessed electroencephalogram (EEG) data, a multilevel wavelet decomposition is applied to obtain the joint distribution information in the two-dimensional time-frequency domain across multiple frequency bands. Subsequently, this information is transformed into three-dimensional spatial data based on the electrode configuration. discriminative joint activity features in the time, frequency, and spatial domains are then extracted by a series of parallel 3d convolutional sub-networks, where 3d channels and spatial attention mechanisms improve the ability to learn critical global and local information. A multi-layer perceptron is finally implemented to integrate the extracted features and further map them to the classification results. Experimental results on the TUSZ dataset, the world's largest publicly available seizure corpus, show that 3d-CBAMNet significantly outperforms the state-of-the-art methods, indicating effectiveness in the seizure type classification task.

关键词： EEG Seizure classification Attention mechanisms 3d convolution

来源：评论

学校读者我要写书评

暂无评论

Optimizing small channel 3d convolution on GPU with tensor core

引用

PARALLEL COMPUTING 2022年 113卷

作者： Jiang, Jiazhi Huang, dan du, Jiangsu Lu, Yutong Liao, Xiangke Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China

In many scenarios, particularly scientific AI applications, algorithm engineers widely adopt more complex convolution, e.g. 3d CNN, to improve the accuracy. Scientific AI applications with 3d-CNN, which tends to train with volumetric datasets, substantially increase the size of the input, which in turn potentially restricts the channel sizes (e.g. less than 64) under the constraints of limited device memory capacity. Since existing convolution implementations tend to split and parallelize computing the small channel convolution from channel dimension, they usually cannot fully exploit the performance of GPU accelerator, in particular that configured with the emerging tensor core. In this work, we target on enhancing the performance of small channel 3d convolution on the GPU platform configured with tensor cores. Our analysis shows that the channel size of convolution has a great effect on the performance of existing convolution implementations, that are memory-bound on tensor core. By leveraging the memory hierarchy characteristics and the WMMA API of tensor core, we propose and implement holistic optimizations for both promoting the data access efficiency and intensifying the utilization of computing units. Experiments show that our implementation can obtain 1.1x-5.4x speedup comparing to the cudNN's implementations for the 3d convolutions on different GPU platforms. We also evaluate our implementations on two practical scientific AI applications and observe up to 1.7x and 2.0x overall speedups compared with using cudNN on V100 GPU.

关键词： 3d convolution GPU Memory hierarchy Tensor core

来源：评论

学校读者我要写书评

暂无评论

Cross-language lipreading by reconstructing Spatio-Temporal relations in 3d convolution

引用

dISPLAYS 2023年 76卷

作者： Feng, Jiangfan Long, Renhua Chongqing Univ Posts & Telecommun Coll Comp Sci & Technol Chongqing Peoples R China

While deep learning (dL) has been making enormous strides in lipreading areas, it is still massively underused in learning, understanding, and producing human language content. Current dL lipreading methods rely on single-channel processing and monolingual datasets, which have a limited ability to adapt to cross-language applications. Here, we propose a novel lipreading driven deep learning framework to create cross-language learning patterns. To evaluate the algorithm's cross-language learning ability, we present a dataset CELR-200 for both Chinese and English in lipreading, containing 200-word classes with more than 80,000 samples. We also propose two Spatio-Temporal Reconstructed 3d convolutional kernels to reconstruct the 3d convolutional Spatio-Temporal relations. By using two STR-3d convolutional kernels, we present two new lipreading models, Serial-STRNet and Parallel-STRNet. These improvements reduce the number of 3d convolutional kernel parameters and improve performance, showing good performance in CELR-200 with 65.68% and 66.35%, respectively. They outperform other lipreading models, achieving an absolute improvement of 2.56% over the state-of-the-art model. Our results identify targets for future investigations and demonstrate that STR-3d convolutional kernels can provide critical insights into lipreading tasks.

关键词： Cross-language lipreading Spatio-Temporal reconstruction 3d convolution convolutional Neural networks Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Feature Compression With 3d Sparse convolution

Feature Compression With 3D Sparse Convolution

引用

2024 Conference on Visual Communications and Image Processing

作者： Ma, Yifan Gao, Changsheng Chen, Qiaoxi Li, Li Liu, dong Sun, Xiaoyan Univ Sci & Technol China MOE Key Lab Brain Inspired Intelligent Percept & Hefei Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Feature compression is an important branch of video coding for machines (VCM). While existing methods draw inspiration from image compression, they have not fully utilized the unique characteristics of features. In this paper, we investigate feature characteristics in two key aspects: dimensionality and sparsity. Our analysis reveals that the low spatial dimensionality and high channel dimensionality of features make traditional 2d convolution-based methods, which usually downsample along spatial dimensions while increasing channels, unsuitable for feature compression. To address this, we propose compressing features using 3d convolution. Additionally, considering the sparsity characteristic, we propose applying sparse convolution to reduce model complexity. To thoroughly investigate the proposed 3d sparse convolution-based method, we verify it with various network structures and input features. Experimental results demonstrate the superiority of our proposed method over traditional 2d convolution-based approaches, highlighting its potential for effective feature compression.

关键词： 3d convolution feature compression sparse convolution video coding for machines

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：