Proceedings of the eighth ACM international conference on Multimedia最新文献

{"title":"Towards virtual videography (poster session)","authors":"Michael Gleicher, J. Masanz","doi":"10.1145/354384.354537","DOIUrl":"https://doi.org/10.1145/354384.354537","url":null,"abstract":"Videographers have developed an art of conveying events in video. Through choices made in cinematography, editing, and post-processing, effective video presentations can be created from events recorded with little or no intrusion. In this paper, we explore systems that bring videography to situations where cost or time issues preclude application of the art. Our goal is to develop virtual videography, that is, systems that can help automate the process of creating an effective video presentation from given footage. In this paper, we discuss how virtual videography systems can be constructed by combining image-based rendering to synthetically generate shots with image understanding to help choose what should be shown to the viewer. To this, visual effects can be added to enhance the presentation, lessening the degradation caused by the medium.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"216 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":"121113878","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":"Demonstration of dynamic class-based router queue management","authors":"J. Chung, M. Claypool","doi":"10.1145/354384.376388","DOIUrl":"https://doi.org/10.1145/354384.376388","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 touters. Two approaches for dealing with Internet congestion at the router are resource reservation and active queue management. Resource reservation uses packet or link scheduling on multiple logical or physical queues to explicitly reserve and allocate output bandwidth to each class of traffic, where a class can be a single flow or a group of similar flows [8]. However, explicit resource reservation changes the current, effective \"best effort\" nature of the Internet, and the algorithmic complexity and state requirements of scheduling make its deployment difficult [11]. Active queue management uses packet queuing disciplines on an outbound router queue to actively handle (or avoid) congestion with the help of cooperative traffic sources, such as TCP. One of the earliest and best-known active queue management mechanism is Random Early Detection (RED) [7]. RED which prevents congestion through monitoring outbound buffers to detect impending congestion, and randomly chooses and notifies senders of network congestion so that they can reduce their transmission rate. While fairly handling congestion for TCP flows, RED has been shown to be extremely unfair in the presence of unresponsive UDP flows [9]. Complicating the above tradit ional congestion control approaches is the presence of mult imedia traffic that has strict delay and j i t ter constraints [1], forcing mult imedia flows to use network protocols other than TCP, some of which may be unresponsive to congestion [11, 9]. In addition, tradit ional router queue management techniques may cause j i t ter [3] which can severely degrade the quality of a mult imedia flow [6]. In order to bet ter manage congestion in the face of varied traffic and in order to bet ter support mult imedia flows, we propose Dynamic-CBT (D-CBT). D-CBT extends the work of [11] and recognizes responsive mult imedia flows while protecting them and TCP flows by adding a simple class-based static bandwidth reservation mechanism to RED. D-CBT fairly allocates bandwidth by dynamically assigning thresholds to each traffic class such tha t the sum of the fair share of flows in each class is assigned to the class at any given time. In addition, as a means to improve mult imedia ji tter, we propose a lightweight packet scheduling mechanism called Cut-In Packet Scheduling (CHIPS) which monitors average enqueue rates of tagged and the other flows, and, on transient congestion awards well-behaved (flow-controlled) mult imedia flows by allowing their packets to 'cut ' in the queue to the average queue length. To evaluate our proposed mechanisms, we implemented D-CBT and CHIPS in a simulator called NS [10] and compared the performance to tha t of CBT and RED. Our studies showed tha t D-CBT improves fairness among different classes of flows and CHIPS improves mult imedia j i t ter without degradi","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"93 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":"127286365","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":"Implementation of aural attributes for simulation of room effects in virtual environments","authors":"Kenji Suzuki, Yuji Nishoji, J. Herder","doi":"10.1145/354384.376349","DOIUrl":"https://doi.org/10.1145/354384.376349","url":null,"abstract":"The audio design for vitural environments includes simulation of acoustical room properties besides specifying sound sources and sinks and their behavior. Virtual environments supporting room reverberation not only gain realism but also provide additional information to the user about surrounding space. Catching the different sound properties by the different spaces requires partitioning the space by the properties of aural spaces. We define soundscape and aural attributes as an application and multimedia content interface. Calculated data on an abstract level is sent to spatialization backends. Part of this research was the implementation of a device driver for the Roland Sound Space Processor. This device not only directionalizes sound sources, but also controls room effects like reverberation.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"2 5 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":"123731488","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 multimodal framework for music inputs (poster session)","authors":"G. Haus, E. Pollastri","doi":"10.1145/354384.354539","DOIUrl":"https://doi.org/10.1145/354384.354539","url":null,"abstract":"The growth of digital music databases imposes new content-based methods of interfacing with stored data; although indexing and retrieval techniques are deeply investigated, an integrated view of querying mechanism has never been established before. Moreover, the multimodal nature of music should be exploited to match the users' expectations as well as their skills. In this paper, we propose a hierarchy of music-interfaces that is suitable for existent prototypes of music information retrieval systems; according to this framework, human/computer interaction should be improved by singing, playing or notating music. Dealing with multiple inputs poses many challenging problems for both their combination and the low-level translation needed to transform an acoustic signal into a symbolic representation. This paper addresses the latter problem in some details, aiming to develop music-interfaces available not only to trained-musician.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"71 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":"130557231","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":"Topic segmentation of news speech using word similarity","authors":"S. Takao, J. Ogata, Y. Ariki","doi":"10.1145/354384.376354","DOIUrl":"https://doi.org/10.1145/354384.376354","url":null,"abstract":"Conventional topic segmentation utilizes cosine measure as the similarity between consecutive passages. However, the cosine measure has a problem that it can not reflect the similarity unless exactly the same words are included in the passages. To solve this problem, in this paper, we propose a method to acquire the word similarity between different words from the input data directly and automatically by managing to collect the same topic sections. Further more, we propose a method to compute the passage similarity based on the word similarity. Finally we propose a method of topic segmentation based on the passage similarity in an unsupervised mode.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"7 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":"116334172","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 video-based augmented reality golf simulator","authors":"A. Govil, Suya You, U. Neumann","doi":"10.1145/354384.376402","DOIUrl":"https://doi.org/10.1145/354384.376402","url":null,"abstract":"Recent advances in augmented reality technology (AR) have opened a tremendous scope of applications. We describe a use of the technology in virtual golf gaming that exemplifies how the technology can be made to suit the specific needs of distinct applications. Various challenges involved challenges involved, proposed solutions, and the results obtained are described.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"9 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":"124493791","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":"Automating the linking of content and concept","authors":"R. Tansley, C. Bird, W. Hall, P. Lewis, M. Weal","doi":"10.1145/354384.376358","DOIUrl":"https://doi.org/10.1145/354384.376358","url":null,"abstract":"In previous work we have described a multimedia system, MAVIS 2, supporting content and concept based retrieval and navigation. A central component of the system is a multimedia thesaurus in which media content is associated with appropriate concepts in a semantic layer. A major challenge is identifying and constructing these associations in a particular application without requiring a huge amount of manual effort. In this paper we propose a two phase approach to the problem. In the first phase, latent semantic analysis is used to associate metadata available for some media objects with concept class descriptions. This facilitate automatic associations to be made with the concept layer of the those media objects. In the second phase, media content matching is used to classify media objects without metadata through their similarity to media objects classified in phase 1.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"128 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":"130259155","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":"Rapid modeling of animated faces from video images","authors":"Zicheng Liu, Zhengyou Zhang, C. Jacobs, Michael F. Cohen","doi":"10.1145/354384.376389","DOIUrl":"https://doi.org/10.1145/354384.376389","url":null,"abstract":"Generating realistic 3D human face models and facial animations has been a persistent challenge in computer graphics. We have developed a system that constructs textured 3D face models from videos with minimal user interaction. Our system takes images and video sequences of a face with an ordinary video camera. After five manual clicks on two images to tell the system where the eye corners, nose top and mouth corners are, the system automatically generates a realistic looking 3D human head model and the constructed model can be animated immediately. A user, with a PC and an ordinary camera, can use our system to generate his/her face model in a few minutes. We will demonstrate the system at the conference.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"4 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":"132998133","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":"Multimedia copyright enforcement on the Internet (panel session)","authors":"J. M. Burger, C. Cookson, D. Kirovski, D. P. Maher, M. Potkonjak, J. Welt","doi":"10.1145/354384.354527","DOIUrl":"https://doi.org/10.1145/354384.354527","url":null,"abstract":"Pand Statement. Technology has made it simple and economical to reproduce, distribute, and publish digital information. While enabling increased legitimate uses of digital media, the potential for misuse is multiplied many fold. Increasing Interact piracy is already producing a billion dollar loss in revenues per year to the music industry. As Internet bandwidth increases, the movie industry is expected to follow the same path. The dynamics of the process is disturbing; for example, Napster's music download web site has experienced a nearly six-fold traffic increase in the second quarter of 2000.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"242 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":"132170238","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":"An application-level multicast architecture for multimedia communications (poster session)","authors":"Kang-Won Lee, Sungwon Ha, Jia-Ru Li, V. Bharghavan","doi":"10.1145/354384.354544","DOIUrl":"https://doi.org/10.1145/354384.354544","url":null,"abstract":"We now first present the core mechanisms of MHPF, i.e. rate adaptat ion and priority-based packet filtering, with respect to a single multicast session, then present a session aggregation mechanism tha t alleviates per-session control and processing at each MHPF server. 2.1 Rate Adaptation Mechanism When the sender transmits a packet, it inserts the epoch id in the packet header. Each receiver counts the number of packets it received in each epoch. Periodically each receiver generates a rate feedback containing recv, epoch, where recv indicates the number of received packets during epoch. The rate feedback is propagated back to the sender along the reverse direction of the multicast tree T. 1 V a r i a b l e s a t t h e t u n n e l s o u r c e i 2 Pl / / s a n d i n g r a t e o f i in the c ~ r r e ~ t e ~ ¢ h 3 p g / / s e n d i n g r a t e o f p a r e n t t u n n e l s o u r c e g in the c u r r e n t epoch 4 P N / / nee downstream ( e s t i m a t e d ) b o t t l e n e c k r a t e f o r n e x t epoch G S e n t / / number o f packetJ sent on i in the c u r r e n t epoch 6 r e ¢ ~ / / number o f packe t s r e c e i v e d by the r e c e i v e r connec ted v i a 7 / / th e f a s t e s t p a t h i n the subarea i n the c u r r e n t epoch 8 A t t h e s t a r t o f e a c h e p o c h 9 The tunnel s o u r c e o f p a r e n t ~ P s e r v e r g in forms i t s s e n d i n g r a t e 10 The tunnel source ~ u pdate s pg I I After t h i s update, the tunnel source i pel-torne 12 i f ( p g < P i -o~) 13 Increase .cons tant +0 t4 else IS i n c r e a e e . ~ o n e t ~ t 4*1 16 A t t h e e n d O f e a c h e p o c h 17 The tumael source i rece i ves reck° and O H f r o 1 the ch l ld 18 i f ( r e c ~ = a e n f ) / / a d d i t i v e I n c r e a s e 29 p( 4-rn~m(pN, p ~ Increase.constant) 20 e lse / / multiplScattve decrease 21 Pi +r ~ i n ( P N , P i X 0 , 5 ) F i g u r e 2: R a t e adaptat ion at t h e M H P F s e r v e r When an MHPF server receives rate feedback on one of its downstream tunnel, it performs the rate control on the tunnel, according to the rate adaptat ion algorithm shown in Figure 2. Essentially the rate adaptat ion algorithm is the popular additive increase multiplicative decrease (AIMD) congestion control: if there was no packet loss in the last epoch (on the fastest path in the subtree rooted at the tunnel source i), i.e. r e e v = sent, then increase the sending rate to probe for more available bandwidth; otherwise, detect congestion and decrease the sending rate. The algorithm presented in Figure 2 has additional conditions so that the rate control algorithm enables the tunnel source to quickly synchronize its sending rate with the downstream bottleneck sending rate 2 by taking the minimum of the calculated sending rate and the est imated downstream bottleneck rate (Figure 2, lines 19, 21). In addition, we introduce 'increase_flag' in order to ensure that the sending rate of a tunnel source i does not increase 2The bottleneck sending rate on ","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":"133207614","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}