发布求助
文献互助 智能选刊 最新文献

2020 IEEE International Conference on Image Processing (ICIP)最新文献

筛选
英文 中文
Kinship Verification From Gait? 从步态验证亲属关系?
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9190787
Salah Eddine Bekhouche, A. Chergui, A. Hadid, Y. Ruichek
{"title":"Kinship Verification From Gait?","authors":"Salah Eddine Bekhouche, A. Chergui, A. Hadid, Y. Ruichek","doi":"10.1109/ICIP40778.2020.9190787","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9190787","url":null,"abstract":"Kinship verification aims to determine whether two persons are kin related or not. This is an emerging topic in computer vision due to its practical potential applications such as family album management. Most of previous works are based on checking kinship from face patterns and more recently from voices. We provide in this paper the first investigation in the literature on kinship verification from gait. The main purpose is to study whether family members do share some gait patterns. As this is a new topic, we started by collecting a new dataset for kinship verification from human gait containing several pairs of video sequences of celebrities and their relatives. The database will be released to the research community for research purposes. Along with the database, we provide results using baseline methods using silhouette and video based analysis. Moreover, we also propose a two-stream 3DCNN to tackle the problem. The preliminary experimental results point out the potential usefulness of gait information for kinship verification.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126600006","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
B-Spline Level Set For Drosophila Image Segmentation 果蝇图像分割的b样条水平集
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191177
Rim Rahali, Yassine Ben Salem, Noura Dridi, H. Dahman
{"title":"B-Spline Level Set For Drosophila Image Segmentation","authors":"Rim Rahali, Yassine Ben Salem, Noura Dridi, H. Dahman","doi":"10.1109/ICIP40778.2020.9191177","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191177","url":null,"abstract":"Segmentation of biological images is a challenging task, due to non convex shapes, intensity inhomogeneity and clustered cells. To address these issues, a new algorithm is proposed based on the B-spline level set method. The implicit function of the level set is modelled as a continuous parametric function represented with the B-spline basis. It is different from the discrete formulation associated with conventional level set. In this paper the proposed framework takes into account properties of biological images. The algorithm is applied to Drosophila images, and compared to conventional level set and Marker Controlled Watershed (MCW). Results show good performance in term of the DICE coefficient, for noisy and noiseless images.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126341103","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: 1
Interactive Separation Network For Image Inpainting 用于图像绘制的交互式分离网络
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191263
Siyuan Li, Luanhao Lu, Zhiqiang Zhang, Xin Cheng, Kepeng Xu, Wenxin Yu, Gang He, Jinjia Zhou, Zhuo Yang
{"title":"Interactive Separation Network For Image Inpainting","authors":"Siyuan Li, Luanhao Lu, Zhiqiang Zhang, Xin Cheng, Kepeng Xu, Wenxin Yu, Gang He, Jinjia Zhou, Zhuo Yang","doi":"10.1109/ICIP40778.2020.9191263","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191263","url":null,"abstract":"Image inpainting, also known as image completion, is the process of filling in the missing region of an incomplete image to make the repaired image visually plausible. Strided convolutional layer learns high-level representations while reducing the computational complexity, but fails to preserve existing detail from the original images (eg, texture, sharp transients), therefore it degrades the generative model in image inpainting task. To reduce the erosion of high-resolution components of images meanwhile maintaining the semantic representation, this paper designs a brand-new network called Interactive Separation Network that progressively decomposites the features into two streams and fuses them. Besides, the rationality of network design and the efficiency of proposed network is demonstrated in the ablation study. To the best of our knowledge, the experimental results of proposed method are superior to state-of-the-art inpainting approaches.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126509869","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: 5
Self-Training Of Graph Neural Networks Using Similarity Reference For Robust Training With Noisy Labels 基于相似性参考的图神经网络鲁棒训练
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191054
Hyoungseob Park, Minki Jeong, Youngeun Kim, Changick Kim
{"title":"Self-Training Of Graph Neural Networks Using Similarity Reference For Robust Training With Noisy Labels","authors":"Hyoungseob Park, Minki Jeong, Youngeun Kim, Changick Kim","doi":"10.1109/ICIP40778.2020.9191054","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191054","url":null,"abstract":"Filtering noisy labels is crucial for robust training of deep neural networks. To train networks with noisy labels, sampling methods have been introduced, which sample the reliable instances to update networks using only sampled data. Since they rarely employ the non-sampled data for training, these methods have a fundamental limitation that they reduce the amount of the training data. To alleviate this problem, our approach aims to fully utilize the whole dataset by leveraging the information of the sampled data. To this end, we propose a novel graph-based learning framework that enables networks to propagate the label information of the sampled data to adjacent data, whether they are sampled or not. Also, we propose a novel self-training strategy to utilize the non-sampled data without labels and to regularize the network update using the information of the sampled data. Our method outperforms state-of-the-art sampling methods.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122234119","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
Upright Adjustment With Graph Convolutional Networks 基于图卷积网络的垂直调整
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9190715
Raehyuk Jung, Sungmin Cho, Junseok Kwon
{"title":"Upright Adjustment With Graph Convolutional Networks","authors":"Raehyuk Jung, Sungmin Cho, Junseok Kwon","doi":"10.1109/ICIP40778.2020.9190715","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9190715","url":null,"abstract":"We present a novel method for the upright adjustment of 360° images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360° images is processed with the CNN for visual feature extraction, and the extracted feature map is converted into a graph that finds a spherical representation of the input. We also introduce a novel loss function to address the issue of discrete probability distributions defined on the surface of a sphere. Experimental results demonstrate that our method outperforms fully connected-based methods.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126757221","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
Channel–Spatial fusion aware net for accurate and fast object Detection 通道-空间融合感知网络用于准确快速的目标检测
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191058
Linhuang Wu, Xiujun Yang, Zhenjia Fan, Chunjun Wang, Z. Chen
{"title":"Channel–Spatial fusion aware net for accurate and fast object Detection","authors":"Linhuang Wu, Xiujun Yang, Zhenjia Fan, Chunjun Wang, Z. Chen","doi":"10.1109/ICIP40778.2020.9191058","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191058","url":null,"abstract":"A major challenge of object detection is that accurate detector is limited by speed due to enormous network, while the lightweight detector can reach real-time but its weak representation ability leads to the expense of accuracy. To overcome the issue, we propose a channel–spatial fusion awareness module (CSFA) to improve the accuracy by enhancing the feature representation of network at the negligible cost of complexity. Given a feature map, our method exploits two parts sequentially, channel awareness and spatial awareness, to reconstruct feature map without deepening the network. Because of the property of CSFA for easy integrating into any layer of CNN architectures, we assemble this module into ResNet-18 and DLA-34 in CenterNet to form a CSFA detector. Results consistently show that CSFA-Net runs in a fairly fast speed, and achieves state-of-the-art, i.e., mAP of 81.12% on VOC2007 and AP of 43.2% on COCO.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126771578","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: 1
CGO: Multiband Astronomical Source Detection With Component-Graphs 基于分量图的多波段天文源探测
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191276
T. X. Nguyen, G. Chierchia, Laurent Najman, A. Venhola, C. Haigh, R. Peletier, M. Wilkinson, Hugues Talbot, B. Perret
{"title":"CGO: Multiband Astronomical Source Detection With Component-Graphs","authors":"T. X. Nguyen, G. Chierchia, Laurent Najman, A. Venhola, C. Haigh, R. Peletier, M. Wilkinson, Hugues Talbot, B. Perret","doi":"10.1109/ICIP40778.2020.9191276","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191276","url":null,"abstract":"Component-graphs provide powerful and complex structures for multi-band image processing. We propose a multiband astronomical source detection framework with the component-graphs relying on a new set of component attributes. We propose two modules to differentiate nodes belong to distinct objects and to detect partial object nodes. Experiments demonstrate an improved capacity at detecting faint objects on a multi-band astronomical dataset.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116043001","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: 2
KRF-SLAM: A Robust AI Slam Based On Keypoint Resampling And Fusion KRF-SLAM:一种基于关键点重采样和融合的鲁棒AI Slam
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191192
Wai Mun Wong, Christopher Lim, Chia-Da Lee, Lilian Wang, Shih-Che Chen, Pei-Kuei Tsung
{"title":"KRF-SLAM: A Robust AI Slam Based On Keypoint Resampling And Fusion","authors":"Wai Mun Wong, Christopher Lim, Chia-Da Lee, Lilian Wang, Shih-Che Chen, Pei-Kuei Tsung","doi":"10.1109/ICIP40778.2020.9191192","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191192","url":null,"abstract":"Artificial Intelligence (AI) based feature extractors provide new possibility in the localization problem because of trainable characteristic. In this paper, the confidence information from AI learning process is used to further improve the accuracy. By resampling interest points based on different confidence thresholds, we are able to pixel-stack highlyconfident interest points to increase their bias for pose optimization. Then, the complementary descriptors are used to describe the pixel stacked interest points. As the result, the proposed Keypoint Resampling and Fusion (KRF) method improves the absolute trajectory error by 40% over state-of the-art vision SLAM algorithm on TUM Freiburg dataset. It is also more robust against tracking lost, and is compatible with existing optimizers.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121148443","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
Blind Image Deblurring With Joint Extreme Channels And L0-Regularized Intensity And Gradient Priors 联合极端通道和0-正则化强度和梯度先验的盲图像去模糊
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191010
Kai Zhou, Peixian Zhuang, J. Xiong, Jin Zhao, Muyao Du
{"title":"Blind Image Deblurring With Joint Extreme Channels And L0-Regularized Intensity And Gradient Priors","authors":"Kai Zhou, Peixian Zhuang, J. Xiong, Jin Zhao, Muyao Du","doi":"10.1109/ICIP40778.2020.9191010","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191010","url":null,"abstract":"The extreme channels prior (ECP) relies on the bright and dark channels of an image, and the corresponding ECP-based methods perform well in blind image deblurring. However, we experimentally observe that the pixel values of dark and bright channels in some images are not concentratedly distributed on 0 and 1 respectively. Based on this observation, we develop a model with a joint prior which combines the extreme channels prior and the $L_{0}-$regularized intensity and gradient prior for blind image deblurring, and previous image deblurring approaches based on dark channel prior, $L_{0^{-}}$ regularized intensity and gradient, and extreme channels prior can be seen as a particular case of our model. Then we derive an efficient optimization algorithm using the half-quadratic splitting method to address the non-convex $L_{0}-$minimization problem. A large number of experiments are finally performed to demonstrate the superiority of the proposed model in details restoration and artifacts removal, and our model outperforms several leading deblurring approaches in terms of subjective results and objective assessments. In addition, our method is more applicable for deblurring natural, text and face images which do not contain many bright or dark pixels.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121190913","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: 5
Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset Egok360: 360以自我为中心的动态人类活动视频数据集
2020 IEEE International Conference on Image Processing (ICIP) Pub Date : 2020-10-01 DOI: 10.1109/ICIP40778.2020.9191256
Keshav Bhandari, Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan
{"title":"Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset","authors":"Keshav Bhandari, Mario A. DeLaGarza, Ziliang Zong, Hugo Latapie, Yan Yan","doi":"10.1109/ICIP40778.2020.9191256","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191256","url":null,"abstract":"Recently, there has been a growing interest in wearable sensors which provides new research perspectives for 360 ° video analysis. However, the lack of 360 ° datasets in literature hinders the research in this field. To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360° Kinetic human activity video dataset (EgoK360). The EgoK360 dataset contains annotations of human activity with different sub-actions, e.g., activity Ping-Pong with four sub-actions which are pickup-ball, hit, bounce-ball and serve. To the best of our knowledge, EgoK360 is the first dataset in the domain of first-person activity recognition with a 360° environmental setup, which will facilitate the egocentric 360 ° video understanding. We provide experimental results and comprehensive analysis of variants of the two-stream network for 360 egocentric activity recognition. The EgoK360 dataset can be downloaded from https://egok360.github.io/.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123864201","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
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信