Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798557
M. Kubo, F. V. Deriggi, A. Sementille, J. Brega, D. Marques, C. Kirner
This paper discusses aspects of computer supported co-operative work (CSCW) and distributed virtual environments. It presents a framework for CSCW in a distributed virtual environment and an application. The application was developed with WorldToolKit, WorldToWorld tools and the Common Object Request Broker Architecture platform. This application is a useful meeting room of the Virtual Environment for Shared Interactive Visualisation (VESIV) Project, developed by the Virtual Reality Group of the Federal University of Sao Carlos.
{"title":"Framework for CSCW applications by using virtual reality","authors":"M. Kubo, F. V. Deriggi, A. Sementille, J. Brega, D. Marques, C. Kirner","doi":"10.1109/ICCIMA.1999.798557","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798557","url":null,"abstract":"This paper discusses aspects of computer supported co-operative work (CSCW) and distributed virtual environments. It presents a framework for CSCW in a distributed virtual environment and an application. The application was developed with WorldToolKit, WorldToWorld tools and the Common Object Request Broker Architecture platform. This application is a useful meeting room of the Virtual Environment for Shared Interactive Visualisation (VESIV) Project, developed by the Virtual Reality Group of the Federal University of Sao Carlos.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122857763","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798541
Y. Hiwatari, K. Fushikida, H. Waki
We present a technique for clustering an index database in order to build an index structure for content based retrieval of video to reduce the query time and make it easier for users to browse the database. The video indexes are classified by an image search engine, and the key index used in the clustering process is chosen as a representative index. When querying a large scale video database, the user can understand the contents of the video database by browsing the representative indexes and can also search for a target video scene efficiently by searching through the representative indexes. We developed a video retrieval system and conducted retrieval experiments in order to compare the retrieval accuracy of three types of index structure. The index structure constructed by k-nearest neighbor clustering achieved higher retrieval accuracy than those constructed by overlapping clustering or serially partitioned clustering.
{"title":"An index structure for content-based retrieval from a video database","authors":"Y. Hiwatari, K. Fushikida, H. Waki","doi":"10.1109/ICCIMA.1999.798541","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798541","url":null,"abstract":"We present a technique for clustering an index database in order to build an index structure for content based retrieval of video to reduce the query time and make it easier for users to browse the database. The video indexes are classified by an image search engine, and the key index used in the clustering process is chosen as a representative index. When querying a large scale video database, the user can understand the contents of the video database by browsing the representative indexes and can also search for a target video scene efficiently by searching through the representative indexes. We developed a video retrieval system and conducted retrieval experiments in order to compare the retrieval accuracy of three types of index structure. The index structure constructed by k-nearest neighbor clustering achieved higher retrieval accuracy than those constructed by overlapping clustering or serially partitioned clustering.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115890176","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798551
Richard O. Sinnott
The formal specification language LOTOS provides a model of systems where the temporal ordering of actions is specified. LOTOS typically does not deal with the specific times at when actions can occur. Most approaches for specifying real time systems in LOTOS have either extended the language, e.g. with timing aspects, or used the language in conjunction with a temporal logic. We argue that such approaches are not always necessary and that LOTOS is much more flexible than sometimes claimed. To support our arguments we show how LOTOS can be used to specify a multitude of timing issues that can be associated with the production and consumption of multimedia flows.
{"title":"Specifying aspects of multimedia in LOTOS","authors":"Richard O. Sinnott","doi":"10.1109/ICCIMA.1999.798551","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798551","url":null,"abstract":"The formal specification language LOTOS provides a model of systems where the temporal ordering of actions is specified. LOTOS typically does not deal with the specific times at when actions can occur. Most approaches for specifying real time systems in LOTOS have either extended the language, e.g. with timing aspects, or used the language in conjunction with a temporal logic. We argue that such approaches are not always necessary and that LOTOS is much more flexible than sometimes claimed. To support our arguments we show how LOTOS can be used to specify a multitude of timing issues that can be associated with the production and consumption of multimedia flows.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131503523","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798548
K. Keeni, K. Nakayama, H. Shimodaira
This study highlights the subject of weight initialization in multi-layer feed-forward networks. Training data is analyzed and the notion of critical point is introduced for determining the initial weights for input to hidden layer synaptic connections. The proposed method has been applied to artificial data. Experimental results show that the proposed method takes almost half the training time required for standard backpropagation.
{"title":"A training scheme for pattern classification using multi-layer feed-forward neural networks","authors":"K. Keeni, K. Nakayama, H. Shimodaira","doi":"10.1109/ICCIMA.1999.798548","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798548","url":null,"abstract":"This study highlights the subject of weight initialization in multi-layer feed-forward networks. Training data is analyzed and the notion of critical point is introduced for determining the initial weights for input to hidden layer synaptic connections. The proposed method has been applied to artificial data. Experimental results show that the proposed method takes almost half the training time required for standard backpropagation.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122913511","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798581
P. Bosc, L. Duval, O. Pivert
The issue of handling imperfect information in a multimedia database system is addressed. The issue of filtering imperfect information appears to be especially crucial in the context of a multimedia system since multimedia data are very often uncertain and/or imprecise. This work is mainly situated in the framework of the possibility theory-based approach which proves to be best suited to qualitative modeling of imprecision/uncertainty when the imperfection pervading the data is of a subjective nature. In the new approach a condition relates to the representation of values, and, as such, returns a satisfaction degree which is certain.
{"title":"On the filtering of imperfect multimedia information by means of representation-based queries","authors":"P. Bosc, L. Duval, O. Pivert","doi":"10.1109/ICCIMA.1999.798581","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798581","url":null,"abstract":"The issue of handling imperfect information in a multimedia database system is addressed. The issue of filtering imperfect information appears to be especially crucial in the context of a multimedia system since multimedia data are very often uncertain and/or imprecise. This work is mainly situated in the framework of the possibility theory-based approach which proves to be best suited to qualitative modeling of imprecision/uncertainty when the imperfection pervading the data is of a subjective nature. In the new approach a condition relates to the representation of values, and, as such, returns a satisfaction degree which is certain.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116890538","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798508
A. Fin
Temporal reasoning is an area of artificial intelligence, very important to many applications. A structure largely used to describe the qualitative temporal information is Allen's interval-based calculus. Inference in the full calculus is NP-hard, therefore some heuristic techniques are needed to solve this problem. A genetic algorithm that achieves a low computational time cost for hard instances of temporal constraint networks is presented.
{"title":"A genetic approach to qualitative temporal reasoning with constraints","authors":"A. Fin","doi":"10.1109/ICCIMA.1999.798508","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798508","url":null,"abstract":"Temporal reasoning is an area of artificial intelligence, very important to many applications. A structure largely used to describe the qualitative temporal information is Allen's interval-based calculus. Inference in the full calculus is NP-hard, therefore some heuristic techniques are needed to solve this problem. A genetic algorithm that achieves a low computational time cost for hard instances of temporal constraint networks is presented.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116950225","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798552
Richard O. Sinnott
In this paper we illustrate how the formal specification language Z can be used to reason about the temporal and throughput constraints associated with multimedia flows of information. In particular we show how it is possible to specify issues related to maximum delays, throughputs and jitter of information flows and how control of these flows can be achieved. What makes out work particularly interesting is that we deal with temporal aspects of systems without the use of a temporal logic. Rather, we highlight the versatility of the Z language in modelling systems with real time constraints.
{"title":"Specifying multimedia configurations in Z","authors":"Richard O. Sinnott","doi":"10.1109/ICCIMA.1999.798552","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798552","url":null,"abstract":"In this paper we illustrate how the formal specification language Z can be used to reason about the temporal and throughput constraints associated with multimedia flows of information. In particular we show how it is possible to specify issues related to maximum delays, throughputs and jitter of information flows and how control of these flows can be achieved. What makes out work particularly interesting is that we deal with temporal aspects of systems without the use of a temporal logic. Rather, we highlight the versatility of the Z language in modelling systems with real time constraints.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116272430","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798523
M. Zorman, V. Podgorelec, P. Kokol, S. H. Babic
We present an intelligent search tool which we developed in order to automate search and evaluation of Web sites. We used TFIDF heuristics to determine term frequency and decision trees to evaluate the quality of sites. Training set for the decision tree contained manually evaluated Web sites. Each Web site was described by the combination of various attributes, complexity metrics and the evaluation. The intelligent search tool is equipped with a user-friendly interface, which enables people to exploit the tool to its limits with minimum effort. For testing purposes, we looked for sites with different content. The set of sites which was the result of using the intelligent search tool has been evaluated by a group of students.
{"title":"Using machine learning techniques for automatic evaluation of Web sites","authors":"M. Zorman, V. Podgorelec, P. Kokol, S. H. Babic","doi":"10.1109/ICCIMA.1999.798523","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798523","url":null,"abstract":"We present an intelligent search tool which we developed in order to automate search and evaluation of Web sites. We used TFIDF heuristics to determine term frequency and decision trees to evaluate the quality of sites. Training set for the decision tree contained manually evaluated Web sites. Each Web site was described by the combination of various attributes, complexity metrics and the evaluation. The intelligent search tool is equipped with a user-friendly interface, which enables people to exploit the tool to its limits with minimum effort. For testing purposes, we looked for sites with different content. The set of sites which was the result of using the intelligent search tool has been evaluated by a group of students.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116502151","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798570
Xuanming. Dong, K. Subramanian
Many existing CSCW (computer supported cooperative work) applications used isolated tools which tend to ignore the existence of others and can't provide detailed state information of cooperative work, although they show a positive impact on overall productivity in cooperative work. To fully make useful of existing CSCW applications and overcome their deficiencies, this paper proposes, defines, designs and implements a cooperative work supporting environment called Viceroy, which deploys a graphical model to represent a cooperative work explicitly. Viceroy provides an infrastructure to plan, design, execute, monitor, and manage CSCW activities on a network, from which participants can get better up-to-date overview and a clear context for performing that cooperative work. Finally, the benefits of Viceroy are presented in this paper.
{"title":"Supporting cooperative work with Viceroy","authors":"Xuanming. Dong, K. Subramanian","doi":"10.1109/ICCIMA.1999.798570","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798570","url":null,"abstract":"Many existing CSCW (computer supported cooperative work) applications used isolated tools which tend to ignore the existence of others and can't provide detailed state information of cooperative work, although they show a positive impact on overall productivity in cooperative work. To fully make useful of existing CSCW applications and overcome their deficiencies, this paper proposes, defines, designs and implements a cooperative work supporting environment called Viceroy, which deploys a graphical model to represent a cooperative work explicitly. Viceroy provides an infrastructure to plan, design, execute, monitor, and manage CSCW activities on a network, from which participants can get better up-to-date overview and a clear context for performing that cooperative work. Finally, the benefits of Viceroy are presented in this paper.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122483983","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798556
J. Silva
Technological evolution dictates the need to make human-computer interactions (HCI) more natural. This need has led to the development of virtual reality (VR), which offers improved user-computer interaction. This study proposes to increase user, HCI designer and software engineer integration, exploring the user's cognitive aspects and VR resources. The HCI designer, working with the user and aided by the appropriate computational support using VR, is able to support the software engineer throughout the entire system development cycle. A prototype of a computational environment is presented with configurable templates (where a template is a predefined virtual environment containing objects that characterize it) to support the development of virtual interfaces, allowing for the exploration of HCI resources in a 3D environment. An example of an application is also given.
{"title":"Development of virtual interfaces using configurable templates","authors":"J. Silva","doi":"10.1109/ICCIMA.1999.798556","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798556","url":null,"abstract":"Technological evolution dictates the need to make human-computer interactions (HCI) more natural. This need has led to the development of virtual reality (VR), which offers improved user-computer interaction. This study proposes to increase user, HCI designer and software engineer integration, exploring the user's cognitive aspects and VR resources. The HCI designer, working with the user and aided by the appropriate computational support using VR, is able to support the software engineer throughout the entire system development cycle. A prototype of a computational environment is presented with configurable templates (where a template is a predefined virtual environment containing objects that characterize it) to support the development of virtual interfaces, allowing for the exploration of HCI resources in a 3D environment. An example of an application is also given.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127011750","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：