发布求助
文献互助 智能选刊 最新文献

2019 IEEE Visual Communications and Image Processing (VCIP)最新文献

筛选
英文 中文
Intra-Frame Compression of Point Cloud Geometry using Boolean Decomposition 基于布尔分解的点云几何帧内压缩
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965783
Rodrigo Rosário, Eduardo Peixoto
{"title":"Intra-Frame Compression of Point Cloud Geometry using Boolean Decomposition","authors":"Rodrigo Rosário, Eduardo Peixoto","doi":"10.1109/VCIP47243.2019.8965783","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965783","url":null,"abstract":"Point clouds are one of the most promising technologies for 3D content representation. Point clouds are a set of points described by their geometry information and additional attributes, of which colour is the most typical. When transmitting a point cloud, both geometry, colour and temporal information need to be transmitted, thus making compression efficiency key in exploiting this technology. In this paper, we propose a lossless intra coder of the geometry information of voxelized point clouds. Instead of using the popular octree approach, we use well-known techniques for coding of bi-level images, as well as a novel boolean decomposition method to further exploit the redundancy within the geometry. Results show that the proposed method outperforms other recent coders on the sequences tested.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126850366","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: 6
Stereoscopic Image Quality Assessment Weighted Guidance by Disparity Map Using Convolutional Neural Network 基于卷积神经网络视差映射的立体图像质量评价加权制导
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965670
Yixiu Ding, Sumei Li, Yongli Chang
{"title":"Stereoscopic Image Quality Assessment Weighted Guidance by Disparity Map Using Convolutional Neural Network","authors":"Yixiu Ding, Sumei Li, Yongli Chang","doi":"10.1109/VCIP47243.2019.8965670","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965670","url":null,"abstract":"In this paper, we propose a new two-column dense Convolutional Neural Network (CNN) for stereoscopic image quality assessment. The input of one column is the cyclopean image which conforms to the binocular combination and rival mechanism in our brain. The input of other column is the disparity map which provides some compensation information for the cyclopean image. More importantly, we employ the features of disparity map to guide and weight the feature maps obtained from the cyclopean image, which is implemented by modifying the structure of Squeeze and Excitation block. This weighting strategy recalibrates the importance of feature maps extracted from cyclopean image. At the end of CNN, we combine the outputs from the two-column through ’Concat’, and then process them to get the final quality score of the stereoscopic image. Experimental results demonstrate that the proposed method can achieve high consistent alignment with subjective assessment.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129188199","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
Online Manhattan Keyframe-based Dense Reconstruction from Indoor Depth Sequences 基于曼哈顿关键帧的室内深度序列密集重建
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965937
Mahdi Yazdanpour, Guoliang Fan, W. Sheng
{"title":"Online Manhattan Keyframe-based Dense Reconstruction from Indoor Depth Sequences","authors":"Mahdi Yazdanpour, Guoliang Fan, W. Sheng","doi":"10.1109/VCIP47243.2019.8965937","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965937","url":null,"abstract":"We present an online framework for dense 3D reconstruction of indoor scenes using sequential Manhattan keyframes. We take advantage of the global geometry of indoor scenes extracted by Manhattan frames and pose optimization to enhance the accuracy and robustness of the reconstructed models. During sequential reconstruction, a Manhattan frame is extracted for each keyframe after surface normal adjustment, and used for a Manhattan keyframe-based planar alignment to initialize the surface registration while a pose graph optimization is used to refine camera poses. The final model is created by integrating the Manhattan keyframes into the unified volumetric model using refined pose estimations. Experimental results demonstrate the advantage of our geometry-based approach to reduce the cumulative registration error and overall geometric drift.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116344592","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
Importance-Aware Filter Selection for Convolutional Neural Network Acceleration 卷积神经网络加速中重要性感知滤波器选择
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965838
Zikun Liu, Zhen Chen, Weiping Li
{"title":"Importance-Aware Filter Selection for Convolutional Neural Network Acceleration","authors":"Zikun Liu, Zhen Chen, Weiping Li","doi":"10.1109/VCIP47243.2019.8965838","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965838","url":null,"abstract":"Convolutional Neural Networks(CNNs) are widely used in many fields, including artificial intelligence, computer vision and video coding. However, CNNs are typically overparameterized and contain significant redundancy. Traditional model acceleration methods mainly rely on specific manual rules. This usually leads to sub-optimal results with relatively limited compression ratio. Recent works have deployed the self-learning agent on the layer-level acceleration but still combined with human-designed criterias. In this paper, we proposed a filter-based model acceleration method to directly and automatically decide which filters should be pruned with the reinforcement learning method DDPG. We designed a novel reward function with the reward shaping technique for the training process. Our method is utilized on the models trained on MNIST and CIFAR-10 datasets and achieves both higher acceleration ratio and less accuracy loss than the conventional methods simultaneously.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116838023","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
Competing Ratio Loss for Multi-class image Classification 多类图像分类中的竞争比损失
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965861
Kecheng Zhang, Xinsheng Wang, Yurong Guo, Zhenbing Zhao, Zhanyu Ma
{"title":"Competing Ratio Loss for Multi-class image Classification","authors":"Kecheng Zhang, Xinsheng Wang, Yurong Guo, Zhenbing Zhao, Zhanyu Ma","doi":"10.1109/VCIP47243.2019.8965861","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965861","url":null,"abstract":"Cross-entropy loss function (CEL) is widely used for training a multi-class classification deep convolutional neural network (DCNN). While CEL has been successfully implemented in image classification tasks, it only focuses on the posterior probability of correct class when the labels of training images are one-hot. It cannot be discriminated against the classes not belong to correct class (wrong classes) directly. Negative Log Likelihood Ratio Loss (NLLR) is proposed to better discriminate the correct class from competing wrong classes. But optimization of the loss function is normally presented as a minimization problem. In training DCNN, the value of NLLR is not constantly positive or negative, which affects the convergence of NLLR adversely. So, we propose competing ratio loss (CRL), which calculates the posterior probability ratio between the correct class and competing wrong classes to better widen the difference between the probability of the correct class and the probabilities of wrong classes, which also assures the value of CRL is constantly positive. Through massive experiments, we demonstrate the effectiveness and robustness of CRL on deep convolutional neural networks, our CRL outperforms CEL and NLLR on CIFAR-10/100 datasets.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117331957","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
Task-in-all Domain Adaptation for Semantic Segmentation 语义分割的全任务域自适应
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965736
Tianyi Zhang, Jingyi Yang, Chuanxia Zheng, Guosheng Lin, Jianfei Cai, A. Kot
{"title":"Task-in-all Domain Adaptation for Semantic Segmentation","authors":"Tianyi Zhang, Jingyi Yang, Chuanxia Zheng, Guosheng Lin, Jianfei Cai, A. Kot","doi":"10.1109/VCIP47243.2019.8965736","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965736","url":null,"abstract":"In this work we tackle the problem of unsupervised domain adaptation for semantic segmentation. One pipeline is to sequentially train image-translation model and the final task segmentation model. In such pipeline, image translation is aimed to generate the translated source-domain images which are visually similar to the target-domain images and then the final task model is trained using the translated images and its corresponding groundtruth. However, the visually optimal translated-images are not necessarily optimal for the final task of segmenting the target-domain images. Thus we propose a Task-in-all pipeline for unsupervised domain adaptation on semantic segmentation, which incorporates image translation and final segmentation task into an end-to-end training pipeline. Our aim is to generate the translated images which better assists the final task, instead of just being visually similar to the target domain images. We show that in the task of adapting from GTA5 to Cityscapes dataset, the segmentation performance of our Task-in-all pipeline outperforms the sequentially training pipeline, with simpler model structure and less training complexity.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114568767","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
LF-TSP: Traveling salesman problem for HEVC-based light-field coding LF-TSP:基于hevc的光场编码的旅行推销员问题
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965837
Kota Imaeda, Kohei Isechi, Keita Takahashi, T. Fujii, Y. Bandoh, T. Miyazawa, Seishi Takamura, A. Shimizu
{"title":"LF-TSP: Traveling salesman problem for HEVC-based light-field coding","authors":"Kota Imaeda, Kohei Isechi, Keita Takahashi, T. Fujii, Y. Bandoh, T. Miyazawa, Seishi Takamura, A. Shimizu","doi":"10.1109/VCIP47243.2019.8965837","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965837","url":null,"abstract":"We studied a coding scheme where light field (LF) images (dense multi-view images) are regarded as a sequence of temporal video frames and encoded with video codecs such as High Efficiency Video Coding (HEVC). An important issue with this scheme is how to determine the frame order of the LF images. We propose a method to find the optimum frame order through a formulation of the traveling salesman problem (TSP). Under the assumption that video codecs are more effective with temporally smooth videos, our method, named LF-TSP, defines frame-to-frame distances for each image pairs in an LF, and attempted to find the shortest route that visits all frames. Experiments showed that our method achieved an overall better rate-distortion performance than several previous methods.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116303050","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
VCIP 2019 Keynote Speeches VCIP 2019主题演讲
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/vcip47243.2019.8965922
{"title":"VCIP 2019 Keynote Speeches","authors":"","doi":"10.1109/vcip47243.2019.8965922","DOIUrl":"https://doi.org/10.1109/vcip47243.2019.8965922","url":null,"abstract":"","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128146282","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
An Improved QoE Evaluation Model for HTTP Adaptive Streaming 一种改进的HTTP自适应流QoE评估模型
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965750
Zaixin Yang, Tiantian He, Li Song, Rong Xie, Xiao Gu
{"title":"An Improved QoE Evaluation Model for HTTP Adaptive Streaming","authors":"Zaixin Yang, Tiantian He, Li Song, Rong Xie, Xiao Gu","doi":"10.1109/VCIP47243.2019.8965750","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965750","url":null,"abstract":"HTTP adaptive streaming (HAS) is an adaptive bitrate streaming technique that enables high quality streaming of media content over the Internet delivered from conventional HTTP web servers. ITU-T Rec. P.1203.3 is the first standardized Quality of Experience model for audiovisual HTTP Adaptive Streaming. It takes into account the subjective impact of HAS-typical effects(such as buffering, quality switches) on users. But the buffering inputs required for the model is too complex and redundant, and it does not consider the impact of the worst video quality on QoE. In the paper we optimize the ITU-T Rec. P.1203.3 model in the above two aspects, simplify model input and improve model accuracy and stability.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"18 70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126707289","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
Gradient-Based Pooling for Convolutional Neural Networks 基于梯度池的卷积神经网络
2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966049
M. Nikzad, Yongsheng Gao, J. Zhou
{"title":"Gradient-Based Pooling for Convolutional Neural Networks","authors":"M. Nikzad, Yongsheng Gao, J. Zhou","doi":"10.1109/VCIP47243.2019.8966049","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8966049","url":null,"abstract":"Pooling layers are an important part of convolutional neural networks (CNNs). They reduce the dimensionality of feature maps and pass salient information to subsequent layers. In this paper, we introduce a novel gradient-based feature pooling method that can down-sample feature maps while better preserving key information. This method considers the spatial gradient of the pixels within a pooling region as a key to select the most possible descriptive information in contrast to the current practice of existing methods that mostly rely on the pixel values. Extensive experiments on different benchmark image classification tasks and CNN architectures demonstrate that the proposed method achieves superior results over existing pooling approaches.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124276893","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
首页 上一页 下一页 尾页
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：604180095
Book学术官方微信
小红书