Over fitting is a common problem for gait recognition algorithms when gait sequences in gallery for training are acquired under a single walking condition. In this paper, we propose an approach based on the random subspace method (RSM) to address such over learning problems. Initially, two-dimensional Principle Component Analysis (2DPCA) is adopted to obtain the full hypothesis space (i.e., eigen space). Multiple inductive biases (i.e., subspaces) are constructed, each with the corresponding basis vectors randomly chosen from the initial eigen space. This procedure can not only largely avoid over adaptation but also facilitate dimension reduction. The final classification is achieved by the decision committee which follows a majority voting criterion from the labeling results of all the subspaces. Experimental results on the benchmark USF Human ID gait database show that the proposed method is a feasible framework for gait recognition under unknown walking conditions.
{"title":"Random Subspace Method for Gait Recognition","authors":"Yu Guan, Chang-Tsun Li, Yongjian Hu","doi":"10.1109/ICMEW.2012.55","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.55","url":null,"abstract":"Over fitting is a common problem for gait recognition algorithms when gait sequences in gallery for training are acquired under a single walking condition. In this paper, we propose an approach based on the random subspace method (RSM) to address such over learning problems. Initially, two-dimensional Principle Component Analysis (2DPCA) is adopted to obtain the full hypothesis space (i.e., eigen space). Multiple inductive biases (i.e., subspaces) are constructed, each with the corresponding basis vectors randomly chosen from the initial eigen space. This procedure can not only largely avoid over adaptation but also facilitate dimension reduction. The final classification is achieved by the decision committee which follows a majority voting criterion from the labeling results of all the subspaces. Experimental results on the benchmark USF Human ID gait database show that the proposed method is a feasible framework for gait recognition under unknown walking conditions.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116920428","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}
There is a strong need to improve the transmission mechanism for eHealth management and multimedia services over a heterogeneous network. Both efficient mechanisms for patient health information access, and communication and delivery over various devices face challenges. Specifically, they include devices with computation and power supply limitations, and HDTV that has a high bandwidth requirement, but limited resources. Network resource limitations are mostly characterized by throughput variations, and delay or transmission errors. An adaptive bit rate of a video in multimedia health services comprise desirable key features that should be considered. In this paper, we propose and demonstrate a cloud computing framework that uses scalable video coding. This has efficient video compression that relieves heterogeneous devices when they execute heavier multimedia applications, use database storage and when delivering mobile health services over limited bandwidth resources. Simulation results show that the proposed scheme achieves a significant improvement in a PSNR-Y gain, as compared to the existing scheme.
{"title":"Cloud-Based E-Health Multimedia Framework for Heterogeneous Network","authors":"Atif Alamri","doi":"10.1109/ICMEW.2012.84","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.84","url":null,"abstract":"There is a strong need to improve the transmission mechanism for eHealth management and multimedia services over a heterogeneous network. Both efficient mechanisms for patient health information access, and communication and delivery over various devices face challenges. Specifically, they include devices with computation and power supply limitations, and HDTV that has a high bandwidth requirement, but limited resources. Network resource limitations are mostly characterized by throughput variations, and delay or transmission errors. An adaptive bit rate of a video in multimedia health services comprise desirable key features that should be considered. In this paper, we propose and demonstrate a cloud computing framework that uses scalable video coding. This has efficient video compression that relieves heterogeneous devices when they execute heavier multimedia applications, use database storage and when delivering mobile health services over limited bandwidth resources. Simulation results show that the proposed scheme achieves a significant improvement in a PSNR-Y gain, as compared to the existing scheme.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127281491","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}
Non-rigid registration of 3D facial surfaces is a crucial step in a variety of computer vision tasks. In this paper, we present a fully automatic 3D face registration method based on the thin plate spline (TPS) and deformable model. To model the non-rigid modality of complex 3D facial surfaces, the thin plate spline is adopted to represent the transformation between 3D faces. The farthest point sampling (FPS) method is used to generate the control points for the thin plate spline transformation automatically. There are two phases for 3D face registration. Firstly, the preliminary registration is obtained by closest points searching between the thin plate spline transformed reference and the target. Then the multi-sample registration is implemented to improve the precision of the registration by using a dynamical reference produced based on deformable model. To eliminate outliers countermeasures are presented in both phases. The experiments on Bu-3dfe and Bjut-3d face databases show that the proposed method is effective and robust.
{"title":"An Automatic Multi-sample 3D Face Registration Method Based on Thin Plate Spline and Deformable Model","authors":"Wenyu Qin, Yongli Hu, Yanfeng Sun, Baocai Yin","doi":"10.1109/ICMEW.2012.85","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.85","url":null,"abstract":"Non-rigid registration of 3D facial surfaces is a crucial step in a variety of computer vision tasks. In this paper, we present a fully automatic 3D face registration method based on the thin plate spline (TPS) and deformable model. To model the non-rigid modality of complex 3D facial surfaces, the thin plate spline is adopted to represent the transformation between 3D faces. The farthest point sampling (FPS) method is used to generate the control points for the thin plate spline transformation automatically. There are two phases for 3D face registration. Firstly, the preliminary registration is obtained by closest points searching between the thin plate spline transformed reference and the target. Then the multi-sample registration is implemented to improve the precision of the registration by using a dynamical reference produced based on deformable model. To eliminate outliers countermeasures are presented in both phases. The experiments on Bu-3dfe and Bjut-3d face databases show that the proposed method is effective and robust.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128209330","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}
Fragment shaders in a graphics pipeline are used to compute the color for each pixel, where lighting, texture loading, and other calculations are involved. The required computing power is proportional to the number of input fragments. In order to improve the power efficiency of mobile GPUs, a content adaptive sampling scheme is proposed to reduce the fragments. The proposed scheme is based on tile-based traversal. For each 4×4 tile, only parts of the fragments are sampled and rendered with the original shader program, and the values of other fragments are interpolated from these rendered fragments if the content checking condition can be passed. With this approach, the sampling patterns are decided adaptively, where more samples are employed for complex regions to avoid quality degradation. Experimental results show that about 30% - 50% fragments can be reduced where high image quality can be still maintained. The proposed scheme can be employed to reduce the power consumption and increase the frame rate for mobile GPUs.
{"title":"Fragment Reduction on Mobile GPU with Content Adaptive Sampling","authors":"Chia-Yang Chang, Yu-Jung Chen, Chia-Ming Chang, Shao-Yi Chien","doi":"10.1109/ICMEW.2012.115","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.115","url":null,"abstract":"Fragment shaders in a graphics pipeline are used to compute the color for each pixel, where lighting, texture loading, and other calculations are involved. The required computing power is proportional to the number of input fragments. In order to improve the power efficiency of mobile GPUs, a content adaptive sampling scheme is proposed to reduce the fragments. The proposed scheme is based on tile-based traversal. For each 4×4 tile, only parts of the fragments are sampled and rendered with the original shader program, and the values of other fragments are interpolated from these rendered fragments if the content checking condition can be passed. With this approach, the sampling patterns are decided adaptively, where more samples are employed for complex regions to avoid quality degradation. Experimental results show that about 30% - 50% fragments can be reduced where high image quality can be still maintained. The proposed scheme can be employed to reduce the power consumption and increase the frame rate for mobile GPUs.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124599019","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}
Automatic music genre classification is an important component in Music Information Retrieval (MIR). It has gained lot of attention lately due to the rapid growth in the use of digital music. Past work in this area has already produced a number of audio features and classification techniques, however, genre classification still remains an unsolved problem. In this paper we explore a hybrid unsupervised/supervised top-down hierarchical classification approach. Most existing work on hierarchical music genre classification relies on human built trees and taxonomies, however these hierarchies may not always translate well into machine classification problems. Therefore, we explore an automatic approach to construct a classification tree through subspace cluster analysis. Experimental results validate the tree building algorithm and provide a new research direction for automatic genre classification. We also addressed the issue of scarcity in publicly available music datasets, by introducing a new dataset containing genre, artist and album labels.
{"title":"A Novel Automatic Hierachical Approach to Music Genre Classification","authors":"H. Ariyaratne, Dengsheng Zhang","doi":"10.1109/ICMEW.2012.104","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.104","url":null,"abstract":"Automatic music genre classification is an important component in Music Information Retrieval (MIR). It has gained lot of attention lately due to the rapid growth in the use of digital music. Past work in this area has already produced a number of audio features and classification techniques, however, genre classification still remains an unsolved problem. In this paper we explore a hybrid unsupervised/supervised top-down hierarchical classification approach. Most existing work on hierarchical music genre classification relies on human built trees and taxonomies, however these hierarchies may not always translate well into machine classification problems. Therefore, we explore an automatic approach to construct a classification tree through subspace cluster analysis. Experimental results validate the tree building algorithm and provide a new research direction for automatic genre classification. We also addressed the issue of scarcity in publicly available music datasets, by introducing a new dataset containing genre, artist and album labels.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129270360","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}
This paper presents architectural performance requirements for a framework dedicated to Augmented Reality (AR) applications. This work has been made as a starting point to evaluation of a framework named ARCS (Augmented Reality Component Systems) allowing rapid-prototyping, development, debugging and monitoring of AR applications. The article first introduces the need of such a dedicated framework and the importance of distribution for AR. It also identifies main features that should be offered by an AR framework and key performance criteria to be satisfied. These are partially inspired by the SPE (Software Performance Engineering) distributed architecture evaluation approach. These criteria are application specific. Thus, we first classify different distributed AR applications in scenarios and extract relevant criteria for each. We also provide a custom assessment protocol inspired by SPE evaluation methodology and based on previously identified criteria. This assessment is application independent as it is based on generic design patterns and most likely scenarios of distribution. Keeping in mind identified criteria and handling existing framework's constraints, a reliable generic AR framework should satisfy all criteria for each application class. Assessment protocol results for each criterion are compared to the typical features and performance that should be offered by an AR system.
{"title":"Distributed Augmented Reality Systems: How Much Performance is Enough?","authors":"M. Chouiten, Jean-Yves Didier, M. Mallem","doi":"10.1109/ICMEW.2012.64","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.64","url":null,"abstract":"This paper presents architectural performance requirements for a framework dedicated to Augmented Reality (AR) applications. This work has been made as a starting point to evaluation of a framework named ARCS (Augmented Reality Component Systems) allowing rapid-prototyping, development, debugging and monitoring of AR applications. The article first introduces the need of such a dedicated framework and the importance of distribution for AR. It also identifies main features that should be offered by an AR framework and key performance criteria to be satisfied. These are partially inspired by the SPE (Software Performance Engineering) distributed architecture evaluation approach. These criteria are application specific. Thus, we first classify different distributed AR applications in scenarios and extract relevant criteria for each. We also provide a custom assessment protocol inspired by SPE evaluation methodology and based on previously identified criteria. This assessment is application independent as it is based on generic design patterns and most likely scenarios of distribution. Keeping in mind identified criteria and handling existing framework's constraints, a reliable generic AR framework should satisfy all criteria for each application class. Assessment protocol results for each criterion are compared to the typical features and performance that should be offered by an AR system.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130569193","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}
In this paper, a classification-based adaptive compression method for computer screen image is presented. This method firstly divides the computer Screen Image into 16×16 non-overlapping blocks, and then every block is classified into three types: text/graphic, pictorial and hybrid blocks based on the characteristics of histogram distribution and the number of colors. For complex text/graphic block, k-Means clustering method is used to reduce the number of colors to improve compression performance, finally the text/graphic block is coded by our proposed lossless coding method, hybrid block is coded by hybrid coding method and the pictorial block is coded by H.264-like intra coding method. Experiment results show that our proposed block classification method exactly distinguishes three block types, color clustering method can effectively reduce the number of colors for complex text/graphic. The compression performance and subjective image quality of our proposed method can outperform JPEG and JP2k.
{"title":"Classification-Based Adaptive Compression Method for Computer Screen Image","authors":"Yanfei Shen, Jintao Li, Zhenmin Zhu, Yun Song","doi":"10.1109/ICMEW.2012.9","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.9","url":null,"abstract":"In this paper, a classification-based adaptive compression method for computer screen image is presented. This method firstly divides the computer Screen Image into 16×16 non-overlapping blocks, and then every block is classified into three types: text/graphic, pictorial and hybrid blocks based on the characteristics of histogram distribution and the number of colors. For complex text/graphic block, k-Means clustering method is used to reduce the number of colors to improve compression performance, finally the text/graphic block is coded by our proposed lossless coding method, hybrid block is coded by hybrid coding method and the pictorial block is coded by H.264-like intra coding method. Experiment results show that our proposed block classification method exactly distinguishes three block types, color clustering method can effectively reduce the number of colors for complex text/graphic. The compression performance and subjective image quality of our proposed method can outperform JPEG and JP2k.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123800052","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}
Most image and video retrieval tools used for large-scale media collections present query results as thumbnails arranged in a grid-like display with each thumbnail preserving the aspect ratio of its corresponding source image or video. Often, the outcome of a query is a set of thumbnails with different aspect ratios, thus a varying amount of padding space is used between the thumbnails in the display. This results in a visually erratic display that conflicts with interface design rules and aesthetic principles stipulating alignment and the usage of straight visual lines to guide the human eye while scanning the display. A solution is to create equally sized thumbnails by using cropping algorithms. However, this may remove useful search information. We investigated a simple alternative: to distort thumbnails to the same aspect ratio in order to provide a calm and structured display with straight lines between thumbnails. In a user experiment we evaluated whether and how much such a horizontal distortion can be applied without hampering visual search performance. The results show that distortion does not notably influence error rate and visual search time.
{"title":"A Visual Search User Study on the Influences of Aspect Ratio Distortion of Preview Thumbnails","authors":"David Ahlström, Klaus Schöffmann","doi":"10.1109/ICMEW.2012.101","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.101","url":null,"abstract":"Most image and video retrieval tools used for large-scale media collections present query results as thumbnails arranged in a grid-like display with each thumbnail preserving the aspect ratio of its corresponding source image or video. Often, the outcome of a query is a set of thumbnails with different aspect ratios, thus a varying amount of padding space is used between the thumbnails in the display. This results in a visually erratic display that conflicts with interface design rules and aesthetic principles stipulating alignment and the usage of straight visual lines to guide the human eye while scanning the display. A solution is to create equally sized thumbnails by using cropping algorithms. However, this may remove useful search information. We investigated a simple alternative: to distort thumbnails to the same aspect ratio in order to provide a calm and structured display with straight lines between thumbnails. In a user experiment we evaluated whether and how much such a horizontal distortion can be applied without hampering visual search performance. The results show that distortion does not notably influence error rate and visual search time.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125591473","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}
Memetics is an approach to interpret, understand and possibly manage communication and knowledge evolution in a Darwinistic way. Meme Media are implementing Memetics. Intelligent Pad has been the earliest Meme Media middleware. Webble Technology is the most recent form of Intelligent Pad. Webbles are objects in a browser window that allow for direct manipulation by drag and drop. One may pick up any Webble and move it over any other one for operational combination. The new Webble is plugged into the previous one and data between them flow through predefined slots. Human users may reconfigure the slot connections of Webbles as desired. The concepts and the technology are setting the stage for new ways of human communication including playful learning. Webbles at the human users' fingertips allow for exploration and explanation by direct manipulation, for collaboration as well as for competition, and for trial and error investigation.
{"title":"Memetic Communication Media - Concepts, Technologies, Applications","authors":"K. Jantke, J. Fujima, O. Arnold, A. Schulz","doi":"10.1109/ICMEW.2012.51","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.51","url":null,"abstract":"Memetics is an approach to interpret, understand and possibly manage communication and knowledge evolution in a Darwinistic way. Meme Media are implementing Memetics. Intelligent Pad has been the earliest Meme Media middleware. Webble Technology is the most recent form of Intelligent Pad. Webbles are objects in a browser window that allow for direct manipulation by drag and drop. One may pick up any Webble and move it over any other one for operational combination. The new Webble is plugged into the previous one and data between them flow through predefined slots. Human users may reconfigure the slot connections of Webbles as desired. The concepts and the technology are setting the stage for new ways of human communication including playful learning. Webbles at the human users' fingertips allow for exploration and explanation by direct manipulation, for collaboration as well as for competition, and for trial and error investigation.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134392866","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}
Yuki Ohkita, Yuya Ohishi, T. Furuya, Ryutarou Ohbuchi
Various algorithms for shape-based retrieval of non-rigid 3D models, with invariance to articulation and/or global deformation, have been developed. A majority of these algorithms assumes that 3D models have mathematically well-defined representations, e.g., closed, manifold mesh. These algorithms are thus not applicable to other types of shape models, for example, those defined as polygon soup. This paper proposes a 3D model retrieval algorithm that accepts diverse 3D shape representations and is is able to compare non-rigid 3D models. The algorithm employs a set of hundreds to thousands of 3D, statistical, local features to describe a 3D model. These features are integrated into a feature vector per 3D model by using bag-of-features approach for efficiency in comparing 3D models and for invariance against articulation and global deformation. Experimental evaluation showed that the algorithm performed well for non-rigid 3D model retrieval.
{"title":"Non-rigid 3D Model Retrieval Using Set of Local Statistical Features","authors":"Yuki Ohkita, Yuya Ohishi, T. Furuya, Ryutarou Ohbuchi","doi":"10.1109/ICMEW.2012.109","DOIUrl":"https://doi.org/10.1109/ICMEW.2012.109","url":null,"abstract":"Various algorithms for shape-based retrieval of non-rigid 3D models, with invariance to articulation and/or global deformation, have been developed. A majority of these algorithms assumes that 3D models have mathematically well-defined representations, e.g., closed, manifold mesh. These algorithms are thus not applicable to other types of shape models, for example, those defined as polygon soup. This paper proposes a 3D model retrieval algorithm that accepts diverse 3D shape representations and is is able to compare non-rigid 3D models. The algorithm employs a set of hundreds to thousands of 3D, statistical, local features to describe a 3D model. These features are integrated into a feature vector per 3D model by using bag-of-features approach for efficiency in comparing 3D models and for invariance against articulation and global deformation. Experimental evaluation showed that the algorithm performed well for non-rigid 3D model retrieval.","PeriodicalId":385797,"journal":{"name":"2012 IEEE International Conference on Multimedia and Expo Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131513477","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：