{"title":"Determining computable scenes in films and their structures using audio-visual memory models","authors":"H. Sundaram, Shih-Fu Chang","doi":"10.1145/354384.354440","DOIUrl":"https://doi.org/10.1145/354384.354440","url":null,"abstract":"In this paper we present novel algorithms for computing scenes and within-scene structures in films. We begin by mapping insights from film-making rules and experimental results from the psychology of audition into a computational scene model. We define a computable scene to be a chunk of audio-visual data that exhibits long-term consistency with regard to three properties: (a) chromaticity (b) lighting (c) ambient sound. Central to the computational model is the notion of a causal, finite-memory viewer model. We segment the audio and video data separately. In each case we determine the degree of correlation of the most recent data in the memory with the past. The respective scene boundaries are determined using local minima and aligned using a nearest neighbor algorithm. We introduce a periodic analysis transform to automatically determine the structure within a scene. We then use statistical tests on the transform to determine the presence of a dialogue. The algorithms were tested on a difficult data set: five commercial films. We take the first hour of data from each of the five films. The best results: scene detection: 88% recall and 72% precision, dialogue detection: 91% recall and 100% precision.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"41 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":"132495838","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}
A. Bachlechner, L. Böszörményi, B. Dörflinger, C. Hofbauer, H. Kosch, Carmen Riedler, R. Tusch
{"title":"The SMOOTH video DB - demonstration of an integrated generic indexing approach","authors":"A. Bachlechner, L. Böszörményi, B. Dörflinger, C. Hofbauer, H. Kosch, Carmen Riedler, R. Tusch","doi":"10.1145/354384.376413","DOIUrl":"https://doi.org/10.1145/354384.376413","url":null,"abstract":"The SMOOTH Video DB is a distributed system proposing an integral query, browsing, and annotation software framework in common with an index database for video media material.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"56 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":"131029559","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}
N. Dimitrova, L. Agnihotri, R. Jasinschi, J. Zimmerman, George Marmaropoulos, T. McGee, S. Dagtas
{"title":"Video scouting demonstration: smart content selection and recording","authors":"N. Dimitrova, L. Agnihotri, R. Jasinschi, J. Zimmerman, George Marmaropoulos, T. McGee, S. Dagtas","doi":"10.1145/354384.376423","DOIUrl":"https://doi.org/10.1145/354384.376423","url":null,"abstract":"Smart video content selection and recording is the best selling feature of the current personal TV receivers like TiVo. These devices operate at the TV program level in that they use electronic program guides and user's program personal preferences to help consumers record and watch programs that match their interests. In this Video Scouting demonstration, we present a system that allows for the filtering and retrieving of TV sub-programs based on user's content preferences. The filtering process is realized via real-time video, audio, and transcript analysis. The demonstrator personalizes the TV experience in the areas of celebrity and financial information. The technology can translate into differentiating storage and set-top box product features for finding your favorite actors, most interesting personalized financial news of the day, commercial compaction and enhancement, and content augmentation with other sources of information such as Web pages and encyclopedia. The demonstrator also reflects our active involvement in the MPEG-7 standard (Content Description Interface).","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"14 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":"116165714","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":"Diogenes: a web search agent for person images","authors":"Y. Aslandogan, Clement T. Yu","doi":"10.1145/354384.376393","DOIUrl":"https://doi.org/10.1145/354384.376393","url":null,"abstract":"Diogenes is a web image search agent that retrieves web pages and associates a person name with each facial image on those pages. To accomplish its goal, Diogenes relies on two types of evidence: Visual and textual. A face detection module examines the images on the web page for human faces. A face recognition module identifies the face by using a database of known person images. A text/HTML analysis module analyses the body of the text with the aim of finding clues about who appears in each image. The outputs of the face detection, text/HTML analysis and face recognition modules are merged using different evidence combination mechanisms to classify each image. Diogenes have been successfully used to retrieve person images from the web with an average precision surpassing those of some commercial image search engines.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"60 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":"114624768","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":"FlyCam: practical panoramic video","authors":"J. Foote, Don Kimber","doi":"10.1145/354384.376401","DOIUrl":"https://doi.org/10.1145/354384.376401","url":null,"abstract":"This demonstration presents a computationally and materially inexpensive system for panoramic video imaging. Digitally combining images from an array of inexpensive video cameras results in a wide-field panoramic camera, from inexpensive off-the-shelf- hardware. Digital processing both corrects lens distortion and seamlessly merges images into a panoramic video image. Electronically selecting a region of this results in a rapidly steerable “virtual camera.”","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"49 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":"122764153","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}
Andrew T. Wilson, M. Lin, B. Yeo, M. Yeung, Dinesh Manocha
{"title":"A video-based rendering acceleration algorithm for interactive walkthroughs","authors":"Andrew T. Wilson, M. Lin, B. Yeo, M. Yeung, Dinesh Manocha","doi":"10.1145/354384.354431","DOIUrl":"https://doi.org/10.1145/354384.354431","url":null,"abstract":"We present a new approach for faster rendering of large synthetic environments using video-based representations. We decompose the large environment into cells and pre-compute video based impostors using MPEG compression to represent sets of objects that are far from each cell. At runtime, we decode the MPEG streams and use rendering algorithms that provide nearly constant-time random access to any frame. The resulting system has been implemented and used for an interactive walkthrough of a model of a house with 260,000 polygons and realistic lighting and textures. It is able to render this model at 16 frames per second (an eightfold improvement over simpler algorithms) on average on a Pentium II PC with an off-the-shelf graphics card.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"94 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":"127026180","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":"Giving meanings to WWW images","authors":"Heng Tao Shen, B. Ooi, K. Tan","doi":"10.1145/354384.376098","DOIUrl":"https://doi.org/10.1145/354384.376098","url":null,"abstract":"Images are increasingly being embedded in HTML documents on the WWW. Such documents over the WWW essentially provides a rich source of image collection from which user can query. Interestingly, the semantics of these images are typically described by their surrounding text. Unfortunately, most WWW image search engines fail to exploit these image semantics and give rise to poor recall and precision performance. In this paper, we propose a novel image representation model called Weight ChainNet. Weight ChainNet is based on lexical chain that represents the semantics of an image from its nearby text. A new formula, called list space model, for computing semantic similarities is also introduced. To further improve the retrieval effectiveness, we also propose two relevance feedback mechanisms. We conducted an extensive performance study on a collection of 5000 images obtained from documents identified by more than 2000 URLs. Our results show that our models and methods outperform existing technique. Moreover, the relevant feedback mechanisms can lead to significantly better retrieval effectiveness.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"26 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":"133415000","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":"Evaluating strategies and systems for content based indexing of person images on the Web","authors":"Y. Aslandogan, Clement T. Yu","doi":"10.1145/354384.354514","DOIUrl":"https://doi.org/10.1145/354384.354514","url":null,"abstract":"Content based indexing of multimedia has always been a challenging task. The enormity and the diversity of the multimedia content on the web adds another dimension to this challenge. In this paper, we examine ways of combining visual and textual information for content based indexing of multimedia on the web. In particular, we examine different methods of combining evidences due to face detection, Text/HTML analysis and face recognition for identifying person images. We provide experimental evaluation of the following strategies: i) Face detection on the image followed by Text/HTML analysis of the containing page; ii) face detection followed by face recognition; iii) face detection followed by a linear combination of evidences due to text/HTML analysis and face recognition; and iv) face detection followed by a Dempster-Shafer combination of evidences due to text/HTML analysis and face recognition. These strategies were implemented in an automatic web search agent named Diogenes1 and compared against some well known web image search engines. The latter includes commercial systems such as Alta Vista, Lycos and Ditto, and a research prototype, WebSEEk. We report the results of our experimental retrievals where Diogenes outperformed these search engines for celebrity image queries in terms of average precision.","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":"133612847","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":"Enabling next generation streaming media networks (keynote session)","authors":"E. Brewer","doi":"10.1145/354384.354393","DOIUrl":"https://doi.org/10.1145/354384.354393","url":null,"abstract":"The proliferation of broadband access, enhancements in production and encoding technologies and increasing consumer demand for rich, high bandwidth content are fueling the need for reliable and cost-effective streaming media delivery networks that ensure a high quality end-user experience. These networks provide a scalable infrastructure for both live and on-demand streaming media. In his keynote, Dr. Brewer will address specific IP infrastructure needs for streaming media delivery; the importance of caching, multicast and bandwidth provisioning; enhancing media delivery with network edge services; and putting it all together to create a high-performance, reliable streaming media delivery network.","PeriodicalId":332091,"journal":{"name":"Proceedings of the eighth ACM international conference on Multimedia","volume":"1 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":"130677671","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":"Immersive panoramic video","authors":"U. Neumann, T. Pintaric, A. Rizzo","doi":"10.1145/354384.376408","DOIUrl":"https://doi.org/10.1145/354384.376408","url":null,"abstract":"The acquisition and presentation of high-resolution panoramic video presents a number of technical difficulties. We demonstrate a system that acquires high-resolution (>3Kx480) panoramic images. These images are recorded at 30Hz frame rates and played back for later viewing. During playback users wear a head-mounted display (HMD) and a head-tracking device that allows them to turn their heads freely to observe the desired portions of the panoramic scene. User impressions initially indicate that the experience produces a strong sense of immersion and this new form of media offers new options for creating immersive simulations./par>","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":"127800795","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}