2012 IEEE International Symposium on Multimedia最新文献_第7页

Using Low Level Gradient Channels for Computationally Efficient Object Detection and Its Application in Logo Detection 基于低梯度通道的高效目标检测及其在Logo检测中的应用

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.51

Yu Chen, V. Thing

引用次数: 0

3D Scene Generation by Learning from Examples 从例子中学习3D场景生成

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.19

Mesfin Dema, H. Sari-Sarraf

{"title":"3D Scene Generation by Learning from Examples","authors":"Mesfin Dema, H. Sari-Sarraf","doi":"10.1109/ISM.2012.19","DOIUrl":"https://doi.org/10.1109/ISM.2012.19","url":null,"abstract":"Due to overwhelming use of 3D models in video games and virtual environments, there is a growing interest in 3D scene generation, scene understanding and 3D model retrieval. In this paper, we introduce a data-driven 3D scene generation approach from a Maximum Entropy (MaxEnt) model selection perspective. Using this model selection criterion, new scenes can be sampled by matching a set of contextual constraints that are extracted from training and synthesized scenes. Starting from a set of random synthesized configurations of objects in 3D, the MaxEnt distribution is iteratively sampled (using Metropolis sampling) and updated until the constraints between training and synthesized scenes match, indicating the generation of plausible synthesized 3D scenes. To illustrate the proposed methodology, we use 3D training desk scenes that are all composed of seven predefined objects with different position, scale and orientation arrangements. After applying the MaxEnt framework, the synthesized scenes show that the proposed strategy can generate reasonably similar scenes to the training examples without any human supervision during sampling. We would like to mention, however, that such an approach is not limited to desk scene generation as described here and can be extended to any 3D scene generation problem.","PeriodicalId":282528,"journal":{"name":"2012 IEEE International Symposium on Multimedia","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122071912","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: 5

Quantifying the Makeup Effect in Female Faces and Its Applications for Age Estimation 女性面部化妆效果的量化及其在年龄估计中的应用

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.29

Ranran Feng, B. Prabhakaran

引用次数: 10

A Motion-Sketch Based Video Retrieval Using MST-CSS Representation 基于MST-CSS表示的运动草图视频检索

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.76

C. Chattopadhyay, Sukhendu Das

引用次数: 4

Mutual Information Based Stereo Correspondence in Extreme Cases 极端情况下基于互信息的立体对应

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.46

Qing Tian, GuangJun Tian

引用次数: 1

Tag Cloud++ - Scalable Tag Clouds for Arbitrary Layouts 标签云++ -可扩展的标签云任意布局

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.66

Minwoo Park, D. Joshi, A. Loui

引用次数: 2

Spatio-temporal Gaussian Mixture Model for Background Modeling 背景建模的时空高斯混合模型

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.73

Y. Soh, Y. Hae, Intaek Kim

引用次数: 12

DLH/CLLS: An Open, Extensible System Design for Prosuming Lecture Recordings and Integrating Multimedia Learning Ecosystems DLH/CLLS:一个开放的，可扩展的系统设计，用于生产讲座录音和集成多媒体学习生态系统

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.97

Kai Michael Höver, Gundolf von Bachhaus, M. Hartle, M. Mühlhäuser

引用次数: 12

A Variational Bayesian Inference Framework for Multiview Depth Image Enhancement 多视角深度图像增强的变分贝叶斯推理框架

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.44

P. Rana, Jalil Taghia, M. Flierl

{"title":"A Variational Bayesian Inference Framework for Multiview Depth Image Enhancement","authors":"P. Rana, Jalil Taghia, M. Flierl","doi":"10.1109/ISM.2012.44","DOIUrl":"https://doi.org/10.1109/ISM.2012.44","url":null,"abstract":"In this paper, a general model-based framework for multiview depth image enhancement is proposed. Depth imagery plays a pivotal role in emerging free-viewpoint television. This technology requires high quality virtual view synthesis to enable viewers to move freely in a dynamic real world scene. Depth imagery of different viewpoints is used to synthesize an arbitrary number of novel views. Usually, the depth imagery is estimated individually by stereo-matching algorithms and, hence, shows lack of inter-view consistency. This inconsistency affects the quality of view synthesis negatively. This paper enhances the inter-view consistency of multiview depth imagery by using a variational Bayesian inference framework. First, our approach classifies the color information in the multiview color imagery. Second, using the resulting color clusters, we classify the corresponding depth values in the multiview depth imagery. Each clustered depth image is subject to further sub clustering. Finally, the resulting mean of the sub-clusters is used to enhance the depth imagery at multiple viewpoints. Experiments show that our approach improves the quality of virtual views by up to 0.25 dB.","PeriodicalId":282528,"journal":{"name":"2012 IEEE International Symposium on Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133131722","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

Video-Based Lane Detection Using a Fast Vanishing Point Estimation Method 基于视频的车道检测快速消失点估计方法

2012 IEEE International Symposium on Multimedia Pub Date : 2012-12-10 DOI: 10.1109/ISM.2012.70

Burak Benligiray, C. Topal, C. Akinlar

{"title":"Video-Based Lane Detection Using a Fast Vanishing Point Estimation Method","authors":"Burak Benligiray, C. Topal, C. Akinlar","doi":"10.1109/ISM.2012.70","DOIUrl":"https://doi.org/10.1109/ISM.2012.70","url":null,"abstract":"Lane detection algorithms constitute a basis for intelligent vehicle systems such as lane tracking and involuntary lane departure detection. In this paper, we propose a simple and video-based lane detection algorithm that uses a fast vanishing point estimation method. The first step of the algorithm is to extract and validate the line segments from the image with a recently proposed line detection algorithm. In the next step, an angle based elimination of line segments is done according to the perspective characteristics of lane markings. This basic operation removes many line segments that belong to irrelevant details on the scene and greatly reduces the number of features to be processed afterwards. Remaining line segments are extrapolated and superimposed to detect the image location where majority of the linear edge features converge. The location found by this efficient operation is assumed to be the vanishing point. Subsequently, an orientation-based removal is done by eliminating the line segments whose extensions do not intersect the vanishing point. The final step is clustering the remaining line segments such that each cluster represents a lane marking or a boundary of the road (i.e. sidewalks, barriers or shoulders). The properties of the line segments that constitute the clusters are fused to represent each cluster with a single line. The nearest two clusters to the vehicle are chosen as the lines that bound the lane that is being driven on. The proposed algorithm works in an average of 12 milliseconds for each frame with 640×480 resolution on a 2.20 GHz Intel CPU. This performance metric shows that the algorithm can be deployed on minimal hardware and still provide real-time performance.","PeriodicalId":282528,"journal":{"name":"2012 IEEE International Symposium on Multimedia","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124620418","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: 35