2019 IEEE Visual Communications and Image Processing (VCIP)最新文献_第4页

Dual-Streams Global Guided Learning for High Dynamic Range Image Reconstruction 高动态范围图像重建的双流全局引导学习

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965798

Junjie Lian, Yongfang Wang, Chuang Wang

引用次数: 1

Multi-path Convolutional Neural Network based on Rectangular Kernel with Path Signature Features for Gesture Recognition 基于路径特征矩形核的多路径卷积神经网络用于手势识别

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965816

Lufan Liao, Xin Zhang, Chenyang Li

{"title":"Multi-path Convolutional Neural Network based on Rectangular Kernel with Path Signature Features for Gesture Recognition","authors":"Lufan Liao, Xin Zhang, Chenyang Li","doi":"10.1109/VCIP47243.2019.8965816","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965816","url":null,"abstract":"Skeleton based gesture recognition has gained more attention due to its wide application and large-scale databases availability. Recent methods designed for skeleton sequence data mainly pay attention to network architecture but ignore an essential characteristic of skeleton sequences that the temporal dimensionality of skeleton sequences is usually higher than its spatial dimensionality. Directly applying CNNs designed for image classification to skeleton-based data can not capture this unique property. Considering this fact, we propose the rectangular convolution and pooling to skeleton sequence data. Temporal features are crucial for gesture action recognition. Further, we introduce path signature features (PSF) to represent temporal variation characteristics of each joint. Moreover, there only exist a few minor distinctions between some gestures. To classify them more accurately, we add two sub-networks to extract discriminative features from two hands respectively. We evaluate our method on three major benchmark gesture datasets, i.e., ChaLearn 2013, ChaLearn 2016 and MSRC-12, and reach the state-of-the-art performance.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"22 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":"116613228","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

Frequency-Domain Analysis Based Exploitation Of Color Channels For Color Image Demosaicking 基于频域分析的彩色通道挖掘彩色图像去马赛克

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966070

S. Jaiswal, V. Jakhetiya, K. Gui, Sharath Chandra Guntuku, A. Singla

引用次数: 0

Depth Estimation with Multi-Resolution Stereo Matching 基于多分辨率立体匹配的深度估计

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965775

Qiuchen Du, Rongke Liu, Yu Pan, Shantong Sun, Shuqiao Sun, Zheng Zheng

{"title":"Depth Estimation with Multi-Resolution Stereo Matching","authors":"Qiuchen Du, Rongke Liu, Yu Pan, Shantong Sun, Shuqiao Sun, Zheng Zheng","doi":"10.1109/VCIP47243.2019.8965775","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965775","url":null,"abstract":"Depth estimation has widely demands in autopilot and scene reconstruction. Although depth estimation has been greatly improved by deep learning, there is still some room for improvement. Usually, stereo-matching-based depth estimation matches low-resolution features and then up-samples depth map to full-resolution. Such methods suffer from low accuracy because of information loss in low-resolution features. To solve this problem, a depth estimation method via multi-resolution gradual-refining stereo matching is proposed. As with classic methods, this method first extracts pyramid features by convolution network and estimates low-resolution depth maps. Then, as an innovation, stereo-matching at each pyramid feature is successively executed using the low-resolution maps as initial depth, which limits search range of stereo-matching for accuracy and efficiency. Results of stereo-matching are used as residuals to refine the depth maps. Experimental results demonstrate that accuracy of depth estimation by the proposed method is significantly improved, but computational complexity does not much increase compared with classic methods.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"47 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":"123695016","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

A Statistical Model for Disocclusions in Depth-based Novel View Synthesis 基于深度的新视图合成中咬合的统计模型

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966071

Jayant Thatte, B. Girod

引用次数: 4

A Progressive Background Updating Based Coding Scheme for Surveillance Videos 一种基于渐进式背景更新的监控视频编码方案

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965904

Meng Li, Yunhui Shi, Wenpeng Ding, Xiaojie Liu, Jiaying Liu, Baocai Yin

引用次数: 0

Spatial and Semantic Relations for Pedestrian Attribute Recognition 行人属性识别的空间语义关系

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965877

Lei Li, Yuan Dong, Fengye Xiong, Hongliang Bai

引用次数: 2

Learn Image Object Co-segmentation with Multi-scale Feature Fusion 学习基于多尺度特征融合的图像目标共分割

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965813

Lina Li, Zhi Liu, Jian Zhang, Xiaofei Zhou

引用次数: 0

Improving Person Search by Adaptive Feature Pyramid-based Multi-Scale Matching 基于自适应特征金字塔的多尺度匹配改进人物搜索

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965743

Binbin Song, Xue Zhou, Wei Xiang, Hao Wen

引用次数: 0

Toward Intelligent Visual Sensing and Low-cost Analysis: A Collaborative Computing Approach 迈向智能视觉感知与低成本分析:一种协同计算方法

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965808

Yan Bai, Ling-yu Duan, Yong Luo, Shiqi Wang, Yonggang Wen, Wen Gao

{"title":"Toward Intelligent Visual Sensing and Low-cost Analysis: A Collaborative Computing Approach","authors":"Yan Bai, Ling-yu Duan, Yong Luo, Shiqi Wang, Yonggang Wen, Wen Gao","doi":"10.1109/VCIP47243.2019.8965808","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965808","url":null,"abstract":"In the big data era, there has been an increasing consensus that the label information, computational resources and communication bandwidth are particularly precious. State-of-the-art research is revolutionizing the vision systems of the smart city, which converts the visual signals from sensory input into feature representations and conveys the compact feature for analysis by using the computational resources of both front and back ends. To deploy a robust model, large amounts of labeled data are usually required, and thereby heavy computational and communication resources are incurred in model training as well as inference. However, the computational resources in front-end devices are usually constrained, and heavy transmission burden is imposed when leveraging multiple models amongst different ends. In this work, we propose a novel collaborative computing approach for intelligent sensing and low-cost analysis, which reduces the requirement of labeled data and communication cost, and balances the computational load in model training and inference. By incorporating the adversarial learning mechanism into collaborative model training, knowledge of different domains can be better exploited. Moreover, the learned models are deployed for inference in a collaborative manner, in which part of model is placed in front-ends for extracting intermediate feature maps, and part of the model remains in back ends for inference with received feature maps. The effectiveness of the proposed approach has been validated in the context of an emerging digital retina system for smart city intelligent applications.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"5 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":"126003287","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