International Conference on Artificial Intelligence and Pattern Recognition最新文献_第4页

Multi-scale saliency using local gradient and global colour features 使用局部梯度和全局颜色特征的多尺度显著性

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2019-08-16 DOI: 10.1145/3357254.3357285

Christopher Cooley, S. Coleman, B. Gardiner, B. Scotney

引用次数: 0

Face expression recognition based on improved convolutional neural network 基于改进卷积神经网络的人脸表情识别

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2019-08-16 DOI: 10.1145/3357254.3357275

Quanming Liu, Jing Zhang, Y. Xin

{"title":"Face expression recognition based on improved convolutional neural network","authors":"Quanming Liu, Jing Zhang, Y. Xin","doi":"10.1145/3357254.3357275","DOIUrl":"https://doi.org/10.1145/3357254.3357275","url":null,"abstract":"Aiming at the problems of huge parameters and network degradation caused by simple linear stacked convolution layers or continuous full connection layers in traditional expression recognition methods, two convolution neural network models are designed through depth separation convolution and residual module respectively to widen and deepen the network. Firstly, model A adopts depth separation convolution instead of regular convolution layer, and the global average pooling layer replaces the final full connection layer, utilizes the methods of dropout, batch normalization, activation function of PReLU and image augmentation to avoid over-fitting effectively. Model B adopts pre-trained ResNet50 model to extract facial features, magnifies the images twice by the SRGAN method. Using ensemble method to fuse model A and B, the accuracy is further improved. To verify the feasibility of the method, the model was tested on the FER2013 facial expression dataset, and the performance was compared with the other facial expression recognition algorithms. The final results showed the improved convolutional neural network (CNN) reached the advanced precision of 73.244% in FER2013 dataset, and the experiment data and the number of model parameters all proved the effectiveness of this method.","PeriodicalId":361892,"journal":{"name":"International Conference on Artificial Intelligence and Pattern Recognition","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133834591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Dense attentional network for pancreas segmentation in abdominal CT scans 腹部CT扫描胰腺分割的密集注意网络

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2019-08-16 DOI: 10.1145/3357254.3357259

Weihao Yu, Huai Chen, Lisheng Wang

{"title":"Dense attentional network for pancreas segmentation in abdominal CT scans","authors":"Weihao Yu, Huai Chen, Lisheng Wang","doi":"10.1145/3357254.3357259","DOIUrl":"https://doi.org/10.1145/3357254.3357259","url":null,"abstract":"Deep neural networks have been widely used in medical image segmentation and they can achieve good results in segmentation of some big organs. However, for some small organs, such as the pancreas in 3D CT images, the segmentation results are usually not satisfactory due to the low proportion. In this paper, we present a novel network --- Dense Attentional Network (DA-Net), to improve the pancreas segmentation in abdominal CT scans. In DA-Net, dense connection is used to combine low-level features of encoder with corresponding features of decoder, which can help to improve the utilization of feature maps (FMs). In addition, a new module for recombination and recalibration of feature maps (RRFM) and a new attentional mechanism --- deep attentional features (DAF), are used, which can excite the most discriminating features. Pancreas is segmented from 3D CT images by a coarse-to-fine mode, in which pancreas is firstly located from 3D CT images by a coarse segmentation network, and then pancreas is further finely segmented by the DA-Net. We evaluate the proposed method with 129 CT images from NIH pancreas dataset and BTCV segmentation challenge, and compare it with several mainstream segmentation networks. Comparing with these networks, our DA-Net has the higher mean DSC of 81.39%. This shows the effectiveness and advantage of the proposed method.","PeriodicalId":361892,"journal":{"name":"International Conference on Artificial Intelligence and Pattern Recognition","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134064663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Recognizing sound signals through spiking neurons and spike-timing-dependent plasticity 通过尖峰神经元识别声音信号和尖峰时间依赖的可塑性

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2019-08-16 DOI: 10.1145/3357254.3357264

Yan Liu, Jiawei Chen, Liujun Chen

引用次数: 1

Attention-based bidirectional gated recurrent unit neural networks for sentiment analysis 基于注意力的双向门控循环单元神经网络情感分析

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2019-08-16 DOI: 10.1145/3357254.3357262

Qing Yu, Hui Zhao, Zuohua Wang

引用次数: 15

Research on recommender algorithm optimization based on statistics and preference model 基于统计和偏好模型的推荐算法优化研究

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2019-08-16 DOI: 10.1145/3357254.3357291

Jia Wang, Xia Song, Q. Jin, Dan Song

引用次数: 0

Super-resolution reconstruction algorithms based on fusion of deep learning mechanism and wavelet 基于深度学习机制和小波融合的超分辨率重构算法

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2019-07-24 DOI: 10.1145/3357254.3358600

Qi Zhang, Huafeng Wang, Tao Du, Sichen Yang, Yuehai Wang, Zhiqiang Xing, Wenle Bai, Yang Yi

{"title":"Super-resolution reconstruction algorithms based on fusion of deep learning mechanism and wavelet","authors":"Qi Zhang, Huafeng Wang, Tao Du, Sichen Yang, Yuehai Wang, Zhiqiang Xing, Wenle Bai, Yang Yi","doi":"10.1145/3357254.3358600","DOIUrl":"https://doi.org/10.1145/3357254.3358600","url":null,"abstract":"In this paper, we consider the problem of super-resolution reconstruction. This is a hot topic because super-resolution reconstruction has a wide range of applications in the medical field, remote sensing monitoring, and criminal investigation. Compared with traditional algorithms, the current super-resolution reconstruction algorithm based on deep learning greatly improves the clarity of reconstructed pictures. Existing work like Super-Resolution Using a Generative Adversarial Network (SRGAN) can effectively restore the texture details of the image. However, experimentally verified that the texture details of the image recovered by the SRGAN are not robust. In order to get super-resolution reconstructed images with richer high-frequency details, we improve the network structure and propose a super-resolution reconstruction algorithm combining wavelet transform and Generative Adversarial Network. The proposed algorithm can efficiently reconstruct high-resolution images with rich global information and local texture details. We have trained our model by PyTorch framework and VOC2012 dataset, and tested it by Set5, Set14, BSD100 and Urban100 test datasets.","PeriodicalId":361892,"journal":{"name":"International Conference on Artificial Intelligence and Pattern Recognition","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124171073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

ClickBAIT: Click-based Accelerated Incremental Training of Convolutional Neural Networks 点击诱饵:基于点击的卷积神经网络加速增量训练

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2017-09-15 DOI: 10.1109/AIPR.2018.8707375

Ervin Teng, João Diogo Falcão, Bob Iannucci

引用次数: 14

A Non-invasive, Multi-modality Approach Based on NIRS and MRI Techniques For Monitoring Intracranial Brain Tumor Angiogenesis 基于近红外光谱(NIRS)和磁共振成像(MRI)技术的无创、多模式颅内脑肿瘤血管生成监测方法

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2005-10-19 DOI: 10.1109/AIPR.2005.10

V. Saxena, J. Nielsen, I. Gonzalez-Gomez, G. Karapetyan, V. Khankaldyyan, M. Nelson, W. Laug

引用次数: 3

A Novel Technique for the Extraction of Depth Information by Gradient Analysis on Grayscale Images 基于梯度分析的灰度图像深度信息提取新技术

International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2004-10-13 DOI: 10.1109/AIPR.2004.7

Li Tao, V. Asari

{"title":"A Novel Technique for the Extraction of Depth Information by Gradient Analysis on Grayscale Images","authors":"Li Tao, V. Asari","doi":"10.1109/AIPR.2004.7","DOIUrl":"https://doi.org/10.1109/AIPR.2004.7","url":null,"abstract":"A technique specifically designed for 3D surface reconstruction of human face in a single grayscale image was developed based on the principle of Shape from Shading (SFS). Lambertian reflectance model was used to obtain the surface gradient information contained in the intensity image. The surface depth was computed by direct integration of surface gradients. The X and Y components of surface gradients were determined based on the assumption that the direction of surface gradient is parallel to the image intensity gradient. In order to determine the signs of the X and Y components of surface gradients, the analysis of image intensity and face detection technique were used to provide the position of critical points based on the 3D characteristics of human face. This algorithm has been applied to synthetic face images with light source direction along z axis, and the reconstructed 3D human face was obtained with good accuracy and high speed. The result produced by our algorithm was also compared with those of other SFS algorithms. The performance of the proposed algorithm indicates that the new concept of combining face detection with SFS will be a promising and useful technique for recovering 3D faces from grayscale images.","PeriodicalId":361892,"journal":{"name":"International Conference on Artificial Intelligence and Pattern Recognition","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123946508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0