Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.779226
F. Pezeshkpour, I. Marshall, R. Elliott, J. Bangham
Many deaf people rely on sign language as their primary mode of communication. They will enjoy enhanced information access if media applications can provide signed commentaries. The advent of multimedia makes such provision possible. We outline a prototype real time subtitle-to-signing translation system, based on the adaptation and integration of existing software components. We describe the development of a framework, using the Tcl/Tk environment, that supports the integration of distributed system components using a basic communications infrastructure. We discuss the development of a virtual human (avatar), deployed in this framework, to perform the signing.
{"title":"Development of a legible deaf-signing virtual human","authors":"F. Pezeshkpour, I. Marshall, R. Elliott, J. Bangham","doi":"10.1109/MMCS.1999.779226","DOIUrl":"https://doi.org/10.1109/MMCS.1999.779226","url":null,"abstract":"Many deaf people rely on sign language as their primary mode of communication. They will enjoy enhanced information access if media applications can provide signed commentaries. The advent of multimedia makes such provision possible. We outline a prototype real time subtitle-to-signing translation system, based on the adaptation and integration of existing software components. We describe the development of a framework, using the Tcl/Tk environment, that supports the integration of distributed system components using a basic communications infrastructure. We discuss the development of a virtual human (avatar), deployed in this framework, to perform the signing.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116224213","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.779232
E. Edirisinghe, Jianmin Jiang
MPEG-4 is an emerging global standard for digital multimedia services. The core development of this video standard is a content based video data structure, which constitutes arbitrarily shaped video objects. The data compression is designed in terms of these video objects rather than frames. Thus, it is a key requirement in the development stages of MPEG-4 to explore possible means of object extraction from video frames. We propose a contour based technique to extract video objects for MPEG-4. The object contours are extracted by convolving a given frame with a Laplacian-of-Gaussian operator, followed by an edge detection process. The contours are later blocked and finally filled with the aid of a pixel based, parity check filling algorithm. Experimental results for several object extractions on 'Lena' and 'Peppers' images are included.
{"title":"A contour analysis based technique to extract objects for MPEG-4","authors":"E. Edirisinghe, Jianmin Jiang","doi":"10.1109/MMCS.1999.779232","DOIUrl":"https://doi.org/10.1109/MMCS.1999.779232","url":null,"abstract":"MPEG-4 is an emerging global standard for digital multimedia services. The core development of this video standard is a content based video data structure, which constitutes arbitrarily shaped video objects. The data compression is designed in terms of these video objects rather than frames. Thus, it is a key requirement in the development stages of MPEG-4 to explore possible means of object extraction from video frames. We propose a contour based technique to extract video objects for MPEG-4. The object contours are extracted by convolving a given frame with a Laplacian-of-Gaussian operator, followed by an edge detection process. The contours are later blocked and finally filled with the aid of a pixel based, parity check filling algorithm. Experimental results for several object extractions on 'Lena' and 'Peppers' images are included.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131686936","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.779120
F. Arman
This paper provides an overview of the issues when migrating from tape-based video systems to complete tape-less systems. The main focus is on workflow and how each system sub-component may effect the workflow. Workflow is discussed in detail due to its overwhelming effects on any organization that decides to undertake and implement change. The sub-systems discussed are storage, networking, media asset management and databases.
{"title":"Tape-less video technologies: issues in workflow transitions","authors":"F. Arman","doi":"10.1109/MMCS.1999.779120","DOIUrl":"https://doi.org/10.1109/MMCS.1999.779120","url":null,"abstract":"This paper provides an overview of the issues when migrating from tape-based video systems to complete tape-less systems. The main focus is on workflow and how each system sub-component may effect the workflow. Workflow is discussed in detail due to its overwhelming effects on any organization that decides to undertake and implement change. The sub-systems discussed are storage, networking, media asset management and databases.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121775365","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.778508
Jia-Ling Koh, Chin-Sung Lee, Arbee L. P. Chen
Traditional research on video data retrieval follows two general approaches. One is based on text annotation and the other on content-based comparison. However these approaches do not fully make use of the meaning implied in a video stream. To improve these approaches, a semantic video model cooperating with a knowledge database is studied. We propose a new semantic video model and focus on presenting the semantic meaning implied in a video. According to the granularity of the meaning implied in a video, a five-level layered structure to model a video stream is proposed. A mechanism is also provided to construct the five levels based on the knowledge categories defined in the knowledge database. The five-level layered structure consists of raw-data levels and semantic-data levels. A uniform semantics representation is proposed to represent the semantic-data levels. This uniform semantics representation allows measuring the similarity of two video streams with different duration. Then an interactive interface can provide browsing and querying video data efficiently through the uniform semantics representation.
{"title":"Semantic video model for content-based retrieval","authors":"Jia-Ling Koh, Chin-Sung Lee, Arbee L. P. Chen","doi":"10.1109/MMCS.1999.778508","DOIUrl":"https://doi.org/10.1109/MMCS.1999.778508","url":null,"abstract":"Traditional research on video data retrieval follows two general approaches. One is based on text annotation and the other on content-based comparison. However these approaches do not fully make use of the meaning implied in a video stream. To improve these approaches, a semantic video model cooperating with a knowledge database is studied. We propose a new semantic video model and focus on presenting the semantic meaning implied in a video. According to the granularity of the meaning implied in a video, a five-level layered structure to model a video stream is proposed. A mechanism is also provided to construct the five levels based on the knowledge categories defined in the knowledge database. The five-level layered structure consists of raw-data levels and semantic-data levels. A uniform semantics representation is proposed to represent the semantic-data levels. This uniform semantics representation allows measuring the similarity of two video streams with different duration. Then an interactive interface can provide browsing and querying video data efficiently through the uniform semantics representation.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128016520","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.778597
Sang Y. Doh, Min Jang
In this paper, we present systems and algorithms for fast forward and fast rewind play system of motion picture streams encoded in standard MPEG system. Many traditional standard MPEG system decoders cannot easily control the MPEG system stream. Especially they have difficulty in controlling fast forward and fast rewind play. We adapt a new concept for our system. We use index data in MPEG system stream. It has compatibility with the standard MPEG decoding method and also covers problems of other models.
{"title":"Fast forward and fast rewind play system based on the MPEG system stream with new concept","authors":"Sang Y. Doh, Min Jang","doi":"10.1109/MMCS.1999.778597","DOIUrl":"https://doi.org/10.1109/MMCS.1999.778597","url":null,"abstract":"In this paper, we present systems and algorithms for fast forward and fast rewind play system of motion picture streams encoded in standard MPEG system. Many traditional standard MPEG system decoders cannot easily control the MPEG system stream. Especially they have difficulty in controlling fast forward and fast rewind play. We adapt a new concept for our system. We use index data in MPEG system stream. It has compatibility with the standard MPEG decoding method and also covers problems of other models.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132748650","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.779235
S. Srinivasan, D. Ponceleón, A. Amir, D. Petkovic
Effective use of digital video can be greatly improved by a combination of two technologies: computer vision for automated video analysis and information visualization for data visualization. The unstructured spatio-temporal nature of video poses tough challenges in the extraction of semantics using fully automated techniques. In the CueVideo project, we combine these automated technologies together with a user interface designed for rapid filtering and comprehension of video content. Our interface introduces two new techniques for viewing video and builds upon existing techniques to provide synergistic views of the video content. We also report on a preliminary user study that compares the efficacy of these views in providing comprehension of video content.
{"title":"\"What is in that video anyway?\": in search of better browsing","authors":"S. Srinivasan, D. Ponceleón, A. Amir, D. Petkovic","doi":"10.1109/MMCS.1999.779235","DOIUrl":"https://doi.org/10.1109/MMCS.1999.779235","url":null,"abstract":"Effective use of digital video can be greatly improved by a combination of two technologies: computer vision for automated video analysis and information visualization for data visualization. The unstructured spatio-temporal nature of video poses tough challenges in the extraction of semantics using fully automated techniques. In the CueVideo project, we combine these automated technologies together with a user interface designed for rapid filtering and comprehension of video content. Our interface introduces two new techniques for viewing video and builds upon existing techniques to provide synergistic views of the video content. We also report on a preliminary user study that compares the efficacy of these views in providing comprehension of video content.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"283 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131815418","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.778544
M. Chan, G. Yu
We introduce a Web De-Compiler (WDC) that extracts Web design information for reuse. Given a Web site, the system extracts design knowledge at several levels: site organization and navigation, page layout, and objects. Objects are regular structures within a page including paragraphs, tables and images. Page layout includes the use of color, fonts, background images, and placement of objects. Design information is extracted by analyzing the HTML tags and images of a Web page. An autonomous agent utilizing the WDC is cataloging all of the designs on the Internet. The design information can be reused in automated and semi-automated Web site design, re-design and analysis.
{"title":"Extracting Web design knowledge: the Web De-Compiler","authors":"M. Chan, G. Yu","doi":"10.1109/MMCS.1999.778544","DOIUrl":"https://doi.org/10.1109/MMCS.1999.778544","url":null,"abstract":"We introduce a Web De-Compiler (WDC) that extracts Web design information for reuse. Given a Web site, the system extracts design knowledge at several levels: site organization and navigation, page layout, and objects. Objects are regular structures within a page including paragraphs, tables and images. Page layout includes the use of color, fonts, background images, and placement of objects. Design information is extracted by analyzing the HTML tags and images of a Web page. An autonomous agent utilizing the WDC is cataloging all of the designs on the Internet. The design information can be reused in automated and semi-automated Web site design, re-design and analysis.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134484732","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.779218
A. François, G. Medioni
We present a system at the junction between Computer Vision and Computer Graphics, to produce a 3-D model of an object as observed in a single image, with a minimum of high-level interaction from a user. The input to our system is a single image. First, the user points, coarsely, at image features (edges) that are subsequently automatically and reproducibly extracted in real-time. The user then performs a high level labeling of the curves (e.g. limb edge, cross-section) and specifies relations between edges (e.g. symmetry, surface or part). NURBS are used as working representation of image edges. The objects described by the user specified, qualitative relationships are then reconstructed either as a set of connected parts modeled as Generalized Cylinders, or as a set of 3-D surfaces for 3-D bilateral symmetric objects. In both cases, the texture is also extracted from the image.
{"title":"A human-assisted system to build 3-D models from a single image","authors":"A. François, G. Medioni","doi":"10.1109/MMCS.1999.779218","DOIUrl":"https://doi.org/10.1109/MMCS.1999.779218","url":null,"abstract":"We present a system at the junction between Computer Vision and Computer Graphics, to produce a 3-D model of an object as observed in a single image, with a minimum of high-level interaction from a user. The input to our system is a single image. First, the user points, coarsely, at image features (edges) that are subsequently automatically and reproducibly extracted in real-time. The user then performs a high level labeling of the curves (e.g. limb edge, cross-section) and specifies relations between edges (e.g. symmetry, surface or part). NURBS are used as working representation of image edges. The objects described by the user specified, qualitative relationships are then reconstructed either as a set of connected parts modeled as Generalized Cylinders, or as a set of 3-D surfaces for 3-D bilateral symmetric objects. In both cases, the texture is also extracted from the image.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130301022","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.778551
T. Shih
The ecosystem is an evolutionary result of natural laws. Food Web (or Food Chain) embeds a set of computation rules of natural balance. Based one the concepts of Food Web, one of the laws that we may learn from the natural besides neural networks and genetic algorithms, we propose a theoretical computation model for mobile agent evolution on the Internet. We define an agent niche overlap graph and agent evolution states. We also propose a set of algorithms, which is used in our multimedia search programs, to simulate agent evolution. Agents are cloned to live on a remote host station based on three different strategies: the brute force strategy, the semi-brute force strategy, and the selective strategy. Evaluations of different strategies are discussed. Guidelines of writing mobile agent programs are proposed. The technique can be used in distributed information retrieval which allows the computation load to be added to servers, but significantly reduces the traffic of network communication.
{"title":"Using Food Web as an evolution computing model for Internet-based multimedia agents","authors":"T. Shih","doi":"10.1109/MMCS.1999.778551","DOIUrl":"https://doi.org/10.1109/MMCS.1999.778551","url":null,"abstract":"The ecosystem is an evolutionary result of natural laws. Food Web (or Food Chain) embeds a set of computation rules of natural balance. Based one the concepts of Food Web, one of the laws that we may learn from the natural besides neural networks and genetic algorithms, we propose a theoretical computation model for mobile agent evolution on the Internet. We define an agent niche overlap graph and agent evolution states. We also propose a set of algorithms, which is used in our multimedia search programs, to simulate agent evolution. Agents are cloned to live on a remote host station based on three different strategies: the brute force strategy, the semi-brute force strategy, and the selective strategy. Evaluations of different strategies are discussed. Guidelines of writing mobile agent programs are proposed. The technique can be used in distributed information retrieval which allows the computation load to be added to servers, but significantly reduces the traffic of network communication.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115031732","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}
Pub Date : 1999-06-07DOI: 10.1109/MMCS.1999.778598
I. Cruz, Parag S. Mahalley
Designing high quality multimedia presentations is a tedious and time consuming task, even for skilled authors. This is particularly true when temporal media such as speech and animation are involved. The focus of our research is to determine whether the multimedia presentation is synchronized or amenable to synchronization. We define a formal framework for verifying temporal synchronization of a presentation, which is based on a modified all-pairs shortest path algorithm.
{"title":"Temporal synchronization in multimedia presentations","authors":"I. Cruz, Parag S. Mahalley","doi":"10.1109/MMCS.1999.778598","DOIUrl":"https://doi.org/10.1109/MMCS.1999.778598","url":null,"abstract":"Designing high quality multimedia presentations is a tedious and time consuming task, even for skilled authors. This is particularly true when temporal media such as speech and animation are involved. The focus of our research is to determine whether the multimedia presentation is synchronized or amenable to synchronization. We define a formal framework for verifying temporal synchronization of a presentation, which is based on a modified all-pairs shortest path algorithm.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115242423","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：