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

FICAL: Focal Inter-Class Angular Loss for Image Classification 图像分类的焦点类间角损失

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965889

Xinran Wei, Dongliang Chang, Jiyang Xie, Yixiao Zheng, Chen Gong, Chuang Zhang, Zhanyu Ma

引用次数: 4

Multi-view Rank Pooling for 3D Object Recognition** 基于多视图秩池的三维物体识别**

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965979

Chaoda Zheng, Yong Xu, Ruotao Xu, Hongyu Chi, Yuhui Quan

引用次数: 1

A Spatio-temporal Hybrid Network for Action Recognition 一个用于动作识别的时空混合网络

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965878

Song Li, Zhicheng Zhao, Fei Su

{"title":"A Spatio-temporal Hybrid Network for Action Recognition","authors":"Song Li, Zhicheng Zhao, Fei Su","doi":"10.1109/VCIP47243.2019.8965878","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965878","url":null,"abstract":"Convolutional Neural Networks (CNNs) are powerful in learning spatial information for static images, while they appear to lose their abilities for action recognition in videos because of the neglecting of long-term motion information. Traditional 3D convolution has high computation complexity and the used Global Average Pooling (GAP) on the bottom of network can also lead to unwanted content loss or distortion. To address above problems, we propose a novel action recognition algorithm by effectively fusing 2D and Pseudo-3D CNN to learn spatio-temporal features of video. First, we use Pseudo-3D CNN with proposed Multi-level pooling module to learn spatio-temporal features. Second, the features output by multi-level pooling module are passed through our proposed processing module to make full use of the rich features. Third, a 2D CNN fed with motion vectors is designed to extract motion patterns, which can be regarded as a supplement of Pseudo-3D CNN to make up for the information lost by RGB images. Fourth, a dependency-based fusion method is proposed to fuse the multi-stream features. Finally, the effectiveness of our proposed action recognition algorithm is demonstrated on public UCF101 and HMDB51 datasets.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"463 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":"122559414","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

Weakly Supervised Learning for Blind Image Quality Assessment 用于盲图像质量评估的弱监督学习

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965868

Weiquan He, Xinbo Gao, Wen Lu, R. Guan

{"title":"Weakly Supervised Learning for Blind Image Quality Assessment","authors":"Weiquan He, Xinbo Gao, Wen Lu, R. Guan","doi":"10.1109/VCIP47243.2019.8965868","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965868","url":null,"abstract":"The blind image quality assessment (BIQA) metric based on deep neural network (DNN) achieves the best evaluation accuracy at present, and the depth of neural networks plays a crucial role for deep learning-based BIQA metric. However, training a DNN for quality assessment is known to be hard because of the lack of labeled data, and getting quality labels for a large number of images is very time consuming and costly. Therefore, training a deep BIQA metric directly will lead to over-fitting in all likelihood. In order to solve this problem, we introduced a weakly supervised approach for learning a deep BIQA metric. First, we pre-trained a novel encoder-decoder architecture by using the training data with weak quality annotations. The annotation is the error map between the distorted image and its undistorted version, which can roughly describes the distribution of distortion and can be easily acquired for training. Next, we fine-tuned the pre-trained encoder on the quality labeled data set. Moreover, we used the group convolution to reduce the parameters of the proposed metric and further reduce the risk of over-fitting. These training strategies, which reducing the risk of over-fitting, enable us to build a very deep neural network for BIQA to have a better performance. Experimental results showed that the proposed model had the state-of-art performance for various images with different distortion types.","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":"122444355","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

Visualization of Dynamic Resource Allocation for HEVC Encoding in FPGA-Accelerated SDN Cloud fpga加速SDN云中HEVC编码动态资源分配可视化

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966042

Panu Sjövall, Mikko Teuho, Arto Oinonen, Jarno Vanne, T. Hämäläinen

引用次数: 2

VCIP 2019 Organizing Committee VCIP 2019组委会

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/vcip47243.2019.8966073

引用次数: 0

Comer-Line-Prediction based Water-tank Detection and Localization 基于角线预测的水箱检测与定位

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965977

Hao Chen, Chongyang Zhang, Yan Luo, Bingkun Zhao, Jiahao Bao

引用次数: 0

Part-guided Network for Pedestrian Attribute Recognition 行人属性识别的部分引导网络

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965957

Ha-eun An, Haonan Fan, Kaiwen Deng, Hai-Miao Hu

引用次数: 7

Asymmetric Supervised Deep Autoencoder for Depth Image based 3D Model Retrieval 基于深度图像的三维模型检索的非对称监督深度自编码器

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965682

A. Siddiqua, Guoliang Fan

引用次数: 4

Comparative Convolutional Neural Network for Younger Face Identification 比较卷积神经网络在年轻人脸识别中的应用

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966026

Liangliang Wang, D. Rajan

引用次数: 0