2012 IEEE International Conference on Multimedia and Expo最新文献_第9页

Leaf Shape Descriptor for Tree Species Identification 树种鉴定用叶形描述符

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.130

Itheri Yahiaoui, O. Mzoughi, N. Boujemaa

引用次数: 40

A Low-Complexity HEVC Intra Prediction Algorithm Based on Level and Mode Filtering 基于水平滤波和模式滤波的低复杂度HEVC帧内预测算法

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.4

Heming Sun, Dajiang Zhou, S. Goto

引用次数: 60

Video Event Detection Using Temporal Pyramids of Visual Semantics with Kernel Optimization and Model Subspace Boosting 基于核优化和模型子空间增强的视觉语义时间金字塔视频事件检测

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.190

N. Codella, A. Natsev, G. Hua, Matthew L. Hill, Liangliang Cao, L. Gong, John R. Smith

引用次数: 9

Frame Rate Up-Conversion for Depth-Based 3D Video 基于深度的3D视频的帧率上转换

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.117

Qingchun Lu, Xiangzhong Fang, Chong Xu, Yongzhe Wang

引用次数: 15

Motion Based Perceptual Distortion and Rate Optimization for Video Coding 基于运动的感知失真和视频编码速率优化

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.140

Xi Wang, Li Su, Qingming Huang, Chunxi Liu, Ling-yu Duan

引用次数: 5

SSIM-Inspired Perceptual Video Coding for HEVC 基于ssim的HEVC感知视频编码

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.175

A. Rehman, Zhou Wang

{"title":"SSIM-Inspired Perceptual Video Coding for HEVC","authors":"A. Rehman, Zhou Wang","doi":"10.1109/ICME.2012.175","DOIUrl":"https://doi.org/10.1109/ICME.2012.175","url":null,"abstract":"Recent advances in video capturing and display technologies, along with the exponentially increasing demand of video services, challenge the video coding research community to design new algorithms able to significantly improve the compression performance of the current H.264/AVC standard. This target is currently gaining evidence with the standardization activities in the High Efficiency Video Coding (HEVC) project. The distortion models used in HEVC are mean squared error (MSE) and sum of absolute difference (SAD). However, they are widely criticized for not correlating well with perceptual image quality. The structural similarity (SSIM) index has been found to be a good indicator of perceived image quality. Meanwhile, it is computationally simple compared with other state-of-the-art perceptual quality measures and has a number of desirable mathematical properties for optimization tasks. We propose a perceptual video coding method to improve upon the current HEVC based on an SSIM-inspired divisive normalization scheme as an attempt to transform the DCT domain frame prediction residuals to a perceptually uniform space before encoding. Based on the residual divisive normalization process, we define a distortion model for mode selection and show that such a divisive normalization strategy largely simplifies the subsequent perceptual rate-distortion optimization procedure. We further adjust the divisive normalization factors based on local content of the video frame. Experiments show that the proposed scheme can achieve significant gain in terms of rate-SSIM performance when compared with HEVC.","PeriodicalId":273567,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121642523","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: 42

Area and Memory Efficient Architectures for 3D Blu-ray-compliant Multimedia Processors 适用于3D蓝光多媒体处理器的区域和内存高效架构

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.81

Chi-Cheng Ju, Tsu-Ming Liu, Y. Chu, Chuang-Chi Chiou, Bin-Jung Tsai, T. Hsiao, Ginny Chen, Pin-Huan Hsu, Chih-Ming Wang, Chun-Chia Chen, Hue-Min Lin, Chia-Yun Cheng, Min-Hao Chiu, Sheng-Jen Wang, Jiun-Yuan Wu, Yuan-Chun Lin, Yung-Chang Chang, Chung-Hung Tsai

引用次数: 0

A Novel View-Level Target Bit Rate Distribution Estimation Technique for Real-Time Multi-view Video Plus Depth 一种新的实时多视点视频加深度视点目标比特率分布估计技术

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.5

M. Cordina, C. J. Debono

引用次数: 4

Pause Intensity: A No-Reference Quality Assessment Metric for Video Streaming in TCP Networks 暂停强度:TCP网络中视频流的无参考质量评估指标

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.148

Colin Bailey, Mirghiasaldin Seyedebrahimi, Xiaohong Peng

{"title":"Pause Intensity: A No-Reference Quality Assessment Metric for Video Streaming in TCP Networks","authors":"Colin Bailey, Mirghiasaldin Seyedebrahimi, Xiaohong Peng","doi":"10.1109/ICME.2012.148","DOIUrl":"https://doi.org/10.1109/ICME.2012.148","url":null,"abstract":"In this paper a full analytic model for pause intensity (PI), a no-reference metric for video quality assessment, is presented. The model is built upon the video play out buffer behavior at the client side and also encompasses the characteristics of a TCP network. Video streaming via TCP produces impairments in play continuity, which are not typically reflected in current objective metrics such as PSNR and SSIM. Recently the buffer under run frequency/probability has been used to characterize the buffer behavior and as a measurement for performance optimization. But we show, using subjective testing, that under run frequency cannot reflect the viewers' quality of experience for TCP based streaming. We also demonstrate that PI is a comprehensive metric made up of a combination of phenomena observed in the play out buffer. The analytical model in this work is verified with simulations carried out on ns-2, showing that the two results are closely matched. The effectiveness of the PI metric has also been proved by subjective testing on a range of video clips, where PI values exhibit a good correlation with the viewers' opinion scores.","PeriodicalId":273567,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129734560","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: 10

CO-LDA: A Semi-supervised Approach to Audio-Visual Person Recognition CO-LDA:一种半监督的视听人物识别方法

2012 IEEE International Conference on Multimedia and Expo Pub Date : 2012-07-09 DOI: 10.1109/ICME.2012.14

Xuran Zhao, N. Evans, J. Dugelay

{"title":"CO-LDA: A Semi-supervised Approach to Audio-Visual Person Recognition","authors":"Xuran Zhao, N. Evans, J. Dugelay","doi":"10.1109/ICME.2012.14","DOIUrl":"https://doi.org/10.1109/ICME.2012.14","url":null,"abstract":"Client models used in Automatic Speaker Recognition (ASR) and Automatic Face Recognition (AFR) are usually trained with labelled data acquired in a small number of menthol sessions. The amount of training data is rarely sufficient to reliably represent the variation which occurs later during testing. Larger quantities of client-specific training data can always be obtained, but manual collection and labelling is often cost-prohibitive. Co-training, a paradigm of semi-supervised machine learning, which can exploit unlabelled data to enhance weakly learned client models. In this paper, we propose a co-LDA algorithm which uses both labelled and unlabelled data to capture greater intersession variation and to learn discriminative subspaces in which test examples can be more accurately classified. The proposed algorithm is naturally suited to audio-visual person recognition because vocal and visual biometric features intrinsically satisfy the assumptions of feature sufficiency and independency which guarantee the effectiveness of co-training. When tested on the MOBIO database, the proposed co-training system raises a baseline identification rate from 71% to 99% while in a verification task the Equal Error Rate (EER) is reduced from 18% to about 1%. To our knowledge, this is the first successful application of co-training in audio-visual biometric systems.","PeriodicalId":273567,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125313126","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: 7