| Formatted contents note |
Introduction / Mark T. Maybury --<br/>Multimedia information extraction : history and state of the art / Mark T. Maybury --<br/>Section 1: Image extraction --<br/>Visual feature localizationfor detecting unique objects in images / Madirakshi Das, Alexander C. Loui, Andrew C. Blose --<br/>Entropy-based analysis of visual and geolocation concepts in images / Keiji Yanai, Hidetoshi Kawakubo, Kobus Barnard --<br/>The meaning of 3D shape and some techniques to extract it / Sven Havemann, Torsten Ullrich, Dieter W. Fellner --<br/>A data-driven meaningful representation of emotional facial expressions / Nicolas Stoiber, Gaspard Breton, Renaud Seguier --<br/>Section 2: Video extraction --<br/>Visual semantics for reducing false positives in video search / Rohini K. Srihari, Adrian Novoschi --<br/>Automated analysis of ideological bias in video / Wei-Hao Lin, Alexander G. Hauptmann --<br/>Multimedia information extraction in a live multilingual news monitoring system / David D. Palmer, Marc B. Reichman, Noah White --<br/>Semantic multimedia extraction using audio and video / Evelyne Tzoukermann, Geetu Ambwani, Amit Bagga [and others] --<br/>Analysis of multimodal natural language content in broadcoast video / Prem Natarajan, Ehry MacRostie, Rohit Prasad --<br/>Web-based multimedia information extraction based on social redundancy / Jose San Pedro, Stefan Siersdorfer, Vaiva Kalnikaite ... [eta l.] --<br/>Information fusion and anomaly detection with uncalibrated cameras in video surveillance / Erhan Baki Ermis, Venkatesh Saligrama, Pierre-Marc Jodoin --<br/>Section 3: Audio, graphics, and behavior extraction --<br/>Automatic detection, indexing, and retrieval of multiple attributes from cross-lingual multimedia data / Qian Hu, Fred J. Goodman, Stanley M. Boykin [and others] --<br/>Information graphics in multimodal documents / Sandra Carberry, Stephanie Elzer, Richard Burns [and others] --<br/>Extracting information from human behavior / Fabio Pianesi, Bruno Lepri, Nadia Mana [and others] --<br/>Section 4: Affect extraction from audio and imagery --<br/>Retrieval of paralinguistic information in broadcasts / Björn Schuller, Martin Wöllmer, Florian Eyben [and others] --<br/>Audience reactions for information extraction about persuasive language in political communication / Marco Guerini, Carlo Strapparava, Oliviero Stock --<br/>The need for affective metadata in content-based recommender systems for images / Marko Tkalčič, Jurij Tasič, Andrej Košir --<br/>Affect-based indexing for multimedia data / Gareth J.F. Jones, Ching Hau Chan --<br/>Section 5: Multimedia annotation and authoring --<br/>Multimedia annotation, querying, and analysis in anvil / Michael Kipp --<br/>Toward formalization of display grammar for interactive media production with multimedia information extraction / Robin Bargar --<br/>Media authoring with ontological reasoning : use case for multimedia information extraction / Insook Choi --<br/>Annoting significant relations on multimedia web documents / Matusala Addisu, Danilo Avola, Paola Bianchi [and others]. |
| Summary, etc |
"The advent of increasingly large consumer collections of audio (e.g., iTunes), imagery (e.g., Flickr), and video (e.g., YouTube) is driving a need not only for multimedia retrieval but also information extraction from and across media. Furthermore, industrial and government collections fuel requirements for stock media access, media preservation, broadcast news retrieval, identity management, and video surveillance. While significant advances have been made in language processing for information extraction from unstructured multilingual text and extraction of objects from imagery and video, these advances have been explored in largely independent research communities who have addressed extracting information from single media (e.g., text, imagery, audio). And yet users need to search for concepts across individual media, author multimedia artifacts, and perform multimedia analysis in many domains.This collection is intended to serve several purposes, including reporting the current state of the art, stimulating novel research, and encouraging cross-fertilization of distinct research disciplines. The collection and integration of a common base of intellectual material will provide an invaluable service from which to teach a future generation of cross disciplinary media scientists and engineers. "-- |
