2019 IEEE Visual Communications and Image Processing (VCIP)最新文献_第2页

VCIP 2019 Tutorials

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965680

引用次数: 0

Enhanced Semantic Features via Attention for Real-Time Visual Tracking 通过注意力增强实时视觉跟踪的语义特征

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965870

M. Geng, Haiying Wang, Yingsen Zeng

引用次数: 0

A Framework for Real-Time Face-Recognition 一种实时人脸识别框架

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965805

Samadhi Wickrama Arachchilage, E. Izquierdo

引用次数: 8

Hybrid Regularization with Elastic Net and Linear Discriminant Analysis for Zero-Shot Image Recognition 弹性网混合正则化与线性判别分析零弹图像识别

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966084

Zhen Qin, Yan Li

{"title":"Hybrid Regularization with Elastic Net and Linear Discriminant Analysis for Zero-Shot Image Recognition","authors":"Zhen Qin, Yan Li","doi":"10.1109/VCIP47243.2019.8966084","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8966084","url":null,"abstract":"Zero-shot learning (ZSL) is the process of recognizing unseen samples from their related classes. Generally, ZSL is realized with the help of some pre-defined semantic information via projecting high dimensional visual features of data samples and class-related semantic vectors into a common embedding space. Although classification can be simply decided through the nearest-neighbor strategy, it usually suffers from problems of domain shift and hubness. In order to address these challenges, majority of researches have introduced regularization with some existing norms, such as lasso or ridge, to constrain the learned embedding. However, the sparse estimation of lasso may cause underfitting of training data, while ridge may introduce bias in the embedding space. In order to resolve these problems, this paper proposes a novel hybrid regularization approach by leveraging elastic net and linear discriminant analysis, and formulates a unified objective function that can be solved efficiently via a synchronous optimization strategy. The proposed method is evaluated on several benchmark image datasets for the task of generalized ZSL. The obtained results demonstrate the superiority of the proposed method over simple regularized methods as well as several previous models.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"140 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":"131891087","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

Improving Action Recognition with the Graph-Neural-Network-based Interaction Reasoning 基于图神经网络的交互推理改进动作识别

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965768

Wu Luo, Chongyang Zhang, Xiaoyun Zhang, Haiyan Wu

引用次数: 3

Quality Assessment for Omnidirectional Video with Consideration of Temporal Distortion Variations 考虑时间失真变化的全向视频质量评估

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966002

Pengwei Zhang, Pan Gao

引用次数: 1

Improving Small-Scale Pedestrian Detection Using Informed Context 利用知情环境改进小规模行人检测

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965786

Zexia Liu, Chongyang Zhang, Yan Luo, Kai Chen, Qiping Zhou, Yunyu Lai

{"title":"Improving Small-Scale Pedestrian Detection Using Informed Context","authors":"Zexia Liu, Chongyang Zhang, Yan Luo, Kai Chen, Qiping Zhou, Yunyu Lai","doi":"10.1109/VCIP47243.2019.8965786","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965786","url":null,"abstract":"Finding small objects is fundamentally challenging because there is little signal on the object to exploit. For the small-scale pedestrian detection, one must use image evidence beyond the pedestrian extent, which is often formulated as context. Unlike existing object detection methods that use adjacent regions or whole image as the context simply, we focus on more informed contexts exploiting and utilizing to improve small-scale pedestrian detection: firstly, one relationship network is developed to utilize the correlation among pedestrian instances in one image; secondly, two spatial regions, overhead area and feet bottom area, are taken as spatial context to exploit the relevance between pedestrian and scenes; at last, GRU [7] (Gated Recurrent Units) modules are introduced to take encoded contexts as input to guide the feature selection and fusion of each proposal. Instead of getting all of the outputs at once, we also iterate twice to refine the detection incrementally. Comprehensive experiments on Caltech Pedestrian [8] and SJTU-SPID [9] datasets, indicate that, with more informed context, the detection performance can be improved significantly, especially for the small-scale pedestrians.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"354 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":"115897091","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

Weather Data Integrated Mask R-CNN for Automatic Road Surface Condition Monitoring 用于路面状况自动监测的天气数据集成掩模R-CNN

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966014

Junyong You

引用次数: 7

Learning a Reliable Decision Making Policy for Robust Tracking 学习一个可靠的鲁棒跟踪决策策略

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8965745

Xiaofeng Huang, Kang-hao Wang, Haibing Yin, Shengsheng Zheng, Xiang Meng, Shengping Zhang

{"title":"Learning a Reliable Decision Making Policy for Robust Tracking","authors":"Xiaofeng Huang, Kang-hao Wang, Haibing Yin, Shengsheng Zheng, Xiang Meng, Shengping Zhang","doi":"10.1109/VCIP47243.2019.8965745","DOIUrl":"https://doi.org/10.1109/VCIP47243.2019.8965745","url":null,"abstract":"Recent years deep learning based visual object trackers have achieved state-of-the-art performance on multiple benchmarks. However, most of these trackers lack an effective mechanism to avoid the wrong template update or re-detect the object when unreliable tracking result appears. In this paper, a novel tracking framework consisting of a tracking network for locating the target and a policy network for decision making is proposed. Firstly, during the off-line training phase, a variant of policy gradient algorithm is adopted, which makes the model converge better and faster. Secondly, current response map and history response map are both fed to the policy network to check the reliability of the tracking result, which effectively distinguishes the response diversity. Finally, an efficient redetection module is proposed to filter a large number of searching areas, which greatly improves the speed. Our proposed algorithm is measured on OTB dataset. Assessment results show that our tracking algorithm improves performance by 5%-6% at the expense of only a small amount of speed.","PeriodicalId":388109,"journal":{"name":"2019 IEEE Visual Communications and Image Processing (VCIP)","volume":"551 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":"117050771","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

RSNet: A Compact Relative Squeezing Net for Image Recognition RSNet:一种用于图像识别的紧凑相对压缩网络

2019 IEEE Visual Communications and Image Processing (VCIP) Pub Date : 2019-12-01 DOI: 10.1109/VCIP47243.2019.8966024

Qi Zhao, Nauman Raoof, Shuchang Lyu, Boxue Zhang, W. Feng

引用次数: 2