2017 IEEE International Conference on Multimedia and Expo (ICME)最新文献_第7页

Non-rigid feature matching for image retrieval using global and local regularizations 基于全局和局部正则化的图像检索非刚性特征匹配

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019441

Yong Ma, Huabing Zhou, Jun Chen, Jingshu Shi, Zhongyuan Wang

{"title":"Non-rigid feature matching for image retrieval using global and local regularizations","authors":"Yong Ma, Huabing Zhou, Jun Chen, Jingshu Shi, Zhongyuan Wang","doi":"10.1109/ICME.2017.8019441","DOIUrl":"https://doi.org/10.1109/ICME.2017.8019441","url":null,"abstract":"In this paper, we propose a probabilistic method for feature matching of near-duplicate images undergoing non-rigid transformations. We start by creating a set of putative correspondences based on the feature similarity, and then focus on removing outliers from the putative set and estimating the transformation as well. This is formulated as a maximum likelihood estimation of a Bayesian model with latent variables indicating whether matches in the putative set are inliers or outliers. We impose the non-parametric global geometrical constraints on the correspondence using Tikhonov regularizers in a reproducing kernel Hilbert space. We also introduce a local geometrical constraint to preserve local structures among neighboring feature points. The problem is solved by using the Expectation Maximization algorithm, and the closed-form solution of the transformation is derived in the maximization step. Moreover, a fast implementation based on sparse approximation is given which reduces the method computation complexity to linearithmic without performance sacrifice. Extensive experiments on real near-duplicate images for both feature matching and image retrieval demonstrate accurate results of the proposed method which outperforms current state-of-the-art methods, especially in case of severe outliers.","PeriodicalId":330977,"journal":{"name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","volume":"80 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128126222","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

Learning deep and sparse feature representation for fine-grained object recognition 学习细粒度对象识别的深度和稀疏特征表示

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019386

M. Srinivas, Yen-Yu Lin, H. Liao

引用次数: 8

Leveraging geometric correlation for input-adaptive facial landmark regression 利用几何相关性进行输入自适应面部地标回归

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019469

Yuyao Feng, Risheng Liu, Xin Fan, Kang Huyan, Zhongxuan Luo

{"title":"Leveraging geometric correlation for input-adaptive facial landmark regression","authors":"Yuyao Feng, Risheng Liu, Xin Fan, Kang Huyan, Zhongxuan Luo","doi":"10.1109/ICME.2017.8019469","DOIUrl":"https://doi.org/10.1109/ICME.2017.8019469","url":null,"abstract":"Facial analysis plays very important role in many vision applications, such as authentication and entertainments. The very early works in the 1990s mostly focus on estimating geometric deformations of facial landmarks to address this task. While in the past several years, more and more efforts have been made to directly learn an appearance regression for facial analysis. Though training regressions on controlled facial images can successfully capture the appearance variations, the performance of these appearance-based models are tightly related to the quantity and quality of the training data. In this paper, we develop a novel framework, named geometric correlated landmark regression (GCLR), to inherit the advantages but overcome limitations of these two categories of methods. Specifically, we first establish a landmark-to-landmark regression to estimate the geometry of facial images. By further incorporating a sparse coding term into the regression framework, we can successfully leverage the geometric correlations between the test image and the shape dictionary, thus significantly enhance the geometry regression performance. Experimental results on various challenging facial data sets verify the effectiveness and efficiency of GCLR.","PeriodicalId":330977,"journal":{"name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127967319","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

Keyword-driven image captioning via Context-dependent Bilateral LSTM 基于上下文相关双边LSTM的关键词驱动图像字幕

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019525

Xiaodan Zhang, Shengfeng He, Xinhang Song, Pengxu Wei, Shuqiang Jiang, Qixiang Ye, Jianbin Jiao, Rynson W. H. Lau

引用次数: 6

Source separation using dictionary learning and deep recurrent neural network with locality preserving constraint 基于字典学习和局部保持约束的深度递归神经网络的源分离

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019516

Pham Tuan, Yuan-Shan Lee, S. Mathulaprangsan, Jia-Ching Wang

引用次数: 4

Automatic skin and hair masking using fully convolutional networks 自动皮肤和头发掩蔽使用全卷积网络

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019339

Siyang Qin, Seongdo Kim, R. Manduchi

引用次数: 16

Hybrid color attribute compression for point cloud data 点云数据的混合颜色属性压缩

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019426

Li Cui, Haiyan Xu, E. Jang

引用次数: 10

Weakly structured information aggregation for upper-body posture assessment using ConvNets 基于卷积神经网络的上半身姿态评估弱结构信息聚合

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019410

Zewei Ding, W. Li, Pichao Wang, P. Ogunbona, Ling Qin

引用次数: 0

Restoration of sea surface temperature images by learning-based and optical-flow-based inpainting 基于学习和光流的海面温度图像修复

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019401

S. Shibata, M. Iiyama, Atsushi Hashimoto, M. Minoh

引用次数: 1

Fashion analysis with a subordinate attribute classification network 基于从属属性分类网络的时尚分析

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019354

Huijing Zhan, Boxin Shi, A. Kot

{"title":"Fashion analysis with a subordinate attribute classification network","authors":"Huijing Zhan, Boxin Shi, A. Kot","doi":"10.1109/ICME.2017.8019354","DOIUrl":"https://doi.org/10.1109/ICME.2017.8019354","url":null,"abstract":"In this paper we deal with two image-based object search tasks in the fashion domain, clothing attribute prediction and cross-domain shoe retrieval. Clothing attribute prediction is about describing the appearances of clothes via semantic attributes and cross-domain shoe retrieval aims at retrieving the same shoe items from online stores given a daily life shoe photo. We jointly solve these two problems by a novel Subordinate Attribute Convolutional Neural Network (SA-CNN), with the newly designed loss function that systematically merges semantic attributes of closer visual appearance to prevent images with obvious visual differences being confused with each other. A three-level feature representation is further developed based on SA-CNN for shoes from different domains. The experimental results demonstrate that the clothing attribute prediction using the proposed SA-CNN achieves better performance than that using traditional features and fine-tuned conventional CNN. Moreover, for the task of cross-domain shoe retrieval, the top-20 retrieval accuracy with deep features extracted from SA-CNN has a significant improvement of 43% compared to that with the pretrained CNN features.","PeriodicalId":330977,"journal":{"name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123911507","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