Ye Lu, C. Hu, Xingquan Zhu, HongJiang Zhang, Qiang Yang
{"title":"A unified framework for semantics and feature based relevance feedback in image retrieval systems","authors":"Ye Lu, C. Hu, Xingquan Zhu, HongJiang Zhang, Qiang Yang","doi":"10.1145/354384.354403","DOIUrl":"https://doi.org/10.1145/354384.354403","url":null,"abstract":"The relevance feedback approach to image retrieval is a powerful technique and has been an active research direction for the past few years. Various ad hoc parameter estimation techniques have been proposed for relevance feedback. In addition, methods that perform optimization on multi-level image content model have been formulated. However, these methods only perform relevance feedback on the low-level image features and fail to address the images' semantic content. In this paper, we propose a relevance feedback technique, iFind, to take advantage of the semantic contents of the images in addition to the low-level features. By forming a semantic network on top of the keyword association on the images, we are able to accurately deduce and utilize the images' semantic contents for retrieval purposes. The accuracy and effectiveness of our method is demonstrated with experimental results on real-world image collections.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134592382","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}
{"title":"MP7TV: a system for content-based querying and retrieval of digital video","authors":"Youngchoon Park, Antonio Pizzarello","doi":"10.1145/354384.376442","DOIUrl":"https://doi.org/10.1145/354384.376442","url":null,"abstract":"The video content retrieval system MP7TV is designed to capture, store, and visually present the information contained in a video sequence. M~7TV uses multi-sensory data fusion techniques and machine learning based on domain and user subjectivity modeling to extract the relevant visual information from compressed video streams, such as MPEG. MP7TV uses advanced spatio-temporal video analysis techniques for spatio-temporal properties such as motion, of video object and highly efficient content based image management environments called PieDB TM for frame based video management. PicDB is an image repository with many sophisticated tools for management and retrieval of pictures. In addition to the treatment of color through proprietary techniques, it combines image processing capabilities with database technologies to provide a powerful system for content based retrieval of visual information. Users of PicDB can create, index, modify, store, query, search, retrieve and edit pictures and synthetic images. All these capabilities are built into MP7TV.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124215769","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}
C. Greenhalgh, Jim Purbrick, S. Benford, M. Craven, Adam Drozd, Ian Taylor
{"title":"Temporal links: recording and replaying virtual environments","authors":"C. Greenhalgh, Jim Purbrick, S. Benford, M. Craven, Adam Drozd, Ian Taylor","doi":"10.1145/354384.354429","DOIUrl":"https://doi.org/10.1145/354384.354429","url":null,"abstract":"Virtual reality (VR) currently lacks the kinds of sophisticated production technologies that are commonly available for established media such as video and audio. This paper introduces the idea of temporal links, which provide a flexible mechanism for replaying past or recent recordings of virtual environments within other real-time virtual environments. Their flexibility arises from a combination of temporal, spatial and presentational properties. Temporal properties determine the relationship between time in a live environment and time in a recording, including the apparent speed and direction of replay. Spatial properties determine the spatial relationship between the environment and the recording. Presentational properties determine the appearance of the recording within the environment. These properties may be fixed, dynamically varied by an application, or directly controlled in real-time by users. Consequently, temporal links have a wide variety of potential uses, including supporting post-production tools for virtual environments, post-exercise debriefing in training simulators, and asynchranous communication such as VR email, as well as providing new forms of content for virtual worlds that refer to past activity. We define temporal links and their properties and describe their implementation in the MASSIVE-3 Collaborative Virtual Environment (CVE) system, focusing on the underlying record and replay mechanisms. We also demonstrate applications for adding new content to an existing virtual world, and a VR post-production editor.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116650572","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}
{"title":"Dynamic-CBT and ChIPS—router support for improved multimedia performance on the Internet","authors":"J. Chung, M. Claypool","doi":"10.1145/354384.354492","DOIUrl":"https://doi.org/10.1145/354384.354492","url":null,"abstract":"The explosive increase in the volume and variety of Internet traffic has placed a growing emphasis on congestion control and fairness in Internet routers. Approaches to the problem of congestion, such as active queue management schemes like Random Early Detection (RED) use congestion avoidance techniques and are successful with TCP flows. Approaches to the problem of fairness, such as Fair Random Early Drop (FRED), keep per-flow state and punish misbehaved, non-TCP flows. Unfortunately, these punishment mechanisms also result in a significant performance drop for multimedia flows that use flow control. We extend Class-Based Threshold (CRT) [12], and propose a new active queue management mechanism as an extension to RED called Dynamic Class-Based Threshold (D- CBT) to improve multimedia performance on the Internet. Also, as an effort to reduce multimedia jitter, we propose a lightweight packet scheduling called Cut-In Packet Scheduling (ChIPS) as an alternative to FIFO packet scheduling. The performance of our proposed mechanisms is measured, analyzed and compared with other mechanisms (RED and CBT) in terms of throughput, fairness and multimedia jitter through simulation using NS. The study shows that D-CBT improves fairness among different classes of flows and ChIPS improves multimedia jitter without degrading fairness.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130768772","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}
{"title":"A reliable multicast webcast protocol for multimedia collaboration and caching","authors":"L. Wright, S. McCanne, Jay Lepreau","doi":"10.1145/354384.354399","DOIUrl":"https://doi.org/10.1145/354384.354399","url":null,"abstract":"Large-scale, multi-point, multimedia conferencing applications designed to facilitate long-distance collaboration are enjoying growing popularity. Usually composed of real-time audio, video and shared-drawing applications, these collaborative environments help render the geographical location of collaborators irrelevant. To complement these existing collaborative applications, it would be useful to have the ability to distribute documents synchronously over the World Wide Web (WWW). One model for synchronized information dissemination within the Web is webcasting in which data are simultaneously distributed to multiple destinations. The WWW's traditional unicast client/server communication model suffers, however, when applied to webcasting; solutions which require many clients to simultaneously fetch data from the origin server using the client/server model will likely cause server and link overload. A number of webcasting solutions have been proposed. Many have limited scalability because they are based on unicast while others use multicast for more scalable data delivery but require server modification or have rigid architectures. We believe that successful webcasting solutions will provide scalable, reliable delivery yet still be compatible with the existing Web infrastructure. In this paper we describe a webcast design that improves upon previous designs by leveraging application level framing (ALF) design methodology. We build upon the Scalable Reliable Multicast (SRM) framework, which is based upon ALF, to create a custom protocol to meet webcast's scalability needs. We employ the protocol in an architecture consisting of two reusable components: a webcache component and a browser control component. We have implemented our design using the MASH multimedia application toolkit and a SRM protocol module called libsrm. We present the results of a simple performance evaluation and report on lessons learned while using MASH and libsrm.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117084977","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}
{"title":"SURFing the home with your TV","authors":"Dimitrios Voutsas, C. Halverson","doi":"10.1145/354384.376365","DOIUrl":"https://doi.org/10.1145/354384.376365","url":null,"abstract":"SURF (Simple UI to Retrieve Favorites) is a system with which a user can interact, through a TV, both with electronic devices inside the house and with the World Wide Web (WWW). The user communicates with the TV by voice in two modes: reactive and proactive. We illustrate how, by speaking naturally, the user can check on locations in the home, or get information from appliances and specific information from the Internet, in a manner that does not interrupt the TV viewing experience.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126696285","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}
S. Paknikar, M. Kankanhalli, K. Ramakrishnan, S. Srinivasan, L. Ngoh
{"title":"A caching and streaming framework for mulitmedia","authors":"S. Paknikar, M. Kankanhalli, K. Ramakrishnan, S. Srinivasan, L. Ngoh","doi":"10.1145/354384.354397","DOIUrl":"https://doi.org/10.1145/354384.354397","url":null,"abstract":"In this paper, we explore the convergence of the caching and streaming technologies for Internet multimedia. The paper describes a design for a streaming and caching architecture to be deployed on broadband networks. The basis of the work is the proposed Internet standard, Real Time Streaming Protocol (RTSP), likely to be the de-facto standard for web-based A/V caching and streaming, in the near future. The proxies are all managed by an `Intelligent Agent' or `Broker' - this has been designed as an enhanced RTSP proxy server that maintains the state information that is so essential in streaming of media data. In addition, all the caching algorithms run on the broker. Having an intelligent agent or broker ensures that the `simple' caching servers can be easily embedded into the network. However, RTSP does nor have the right model for doing broker based streaming/caching architecture. The work reported here is an attempt to contribute towards that end.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127594840","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}
{"title":"Data allocation algorithms for distributed video servers","authors":"J. Wang, R. Guha","doi":"10.1145/354384.376367","DOIUrl":"https://doi.org/10.1145/354384.376367","url":null,"abstract":"In this paper, We discuss the server level data allocation problems in the distributed Video-on-Demand systems. We proposed two data allocation algorithms, Bandwidth Weighted Partition (BWP) algorithm and Popularity Based (PB) algorithm, based on the bandwidth and storage capacity limits of the distributed multimedia servers. We compare those two algorithms with the traditional Round Robin (RR) algorithm. The analysis and simulation studies show that PB algorithm is a simple and practical video data allocation algorithm for the distributed video servers. It provides near optimal system performance in any system condition.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"178 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113988603","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}
{"title":"Mediacaptain - a demo","authors":"Florian Mueller","doi":"10.1145/354384.379089","DOIUrl":"https://doi.org/10.1145/354384.379089","url":null,"abstract":"The mediacaptain is a system that facilitates indexing, browsing, summarizing and retrieval of video, on the Web with the support of supplementary material. The demo is available over the Web at htt://www.mediacaptain.com. It is a presentation about the mediacaptain using the features of the mediacaptain. In order to experience all the possibilities of the mediacaptain, it is advisable to watch the video at the given URL and make use of the provided functionality.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131159991","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}
{"title":"SmartWatch: an automated video event finder","authors":"S. Dagtas, T. McGee, M. Abdel-Mottaleb","doi":"10.1145/354384.376437","DOIUrl":"https://doi.org/10.1145/354384.376437","url":null,"abstract":"In this paper, we present an automated video event detection system that combines textual an aural analysis techniques.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134542126","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}