主讲人：Dr. Benoit Huet (Eurecom France)
时间：2014 年 7 月 12 日（周六）下午 2:30-3:30
地点：张江校区计算机楼 405
联系人：姜育刚（ygj@fudan.edu.cn）
Abstract:
Media hyperlinking consists in linking together media based on their content, uncovering the relation between them. It is becoming an important functionality for providing users with a way to navigate between video entities illustrating various related facets of the original topic and satisfy their information needs. Thanks to such approaches, multimedia search can often be replaced by recommendation. A particular usage of hyperlinking is to provide, through a second screen application, extra information or content about the video watched on a main screen (TV). In this talk, we will focus on multimodal content analysis for media search and hyperlinking: the task at hand consists in locating and identifying relevant media items, and displaying them on the second screen. Currently, popular search engines retrieve documents and media items on the basis of textual content. Integrating the visual information within the text-based search for video and image retrieval is still a hot research topic. Here, a video search and hyperlinking framework based on using visual information to enrich the classic text-based search for video retrieval is proposed and evaluated. The framework extends conventional text-based search by fusing together text and visual scores, obtained from video subtitles (or automatic speech recognition) and visual concept detectors respectively. We attempt to overcome the so called problems of semantic and intention gap by automatically mapping user’s textual query to semantic visual concepts. With the proposed framework, we endeavor to show experimentally, on a set of real world scenarios, that visual cues can effectively contribute to the quality improvement of video retrieval. Experimental results show that mapping text-based queries to visual concepts improves the performance of the search and hyperlinking system.
Bio:
Dr. Benoit Huet is Assistant Professor in the multimedia information processing group of Eurecom (France). He received his BSc degree in computer science and engineering from the École Supérieure de Technologie Électrique (Groupe ESIEE, France) in 1992. In 1993, he was awarded the MSc degree in Artificial Intelligence from the University of Westminster (UK) with distinction, where he then spent two years working as a research and teaching assistant. He received his DPhil degree in Computer Science from the University of York (UK) for his research on the topic of object recognition from large databases. He was awarded the HDR (Habilitation to Direct Research) from the University of Nice Sophia Antipolis, France, in October 2012 on the topic of Multimedia Content Understanding: Bringing Context to Content. He is associate editor for IEEE Multimedia, Multimedia Tools and Application (Springer) and Multimedia Systems (Springer) and has been guest editor for a number of special issues (EURASIP Journal on Image and Video Processing, IEEE Multimedia). He regularly serves on the technical program committee of the top conference of the field (ACM MM/ICMR, IEEE ICME/ICIP). He is chairing the IEEE MMTC Interest Group on Visual Analysis, Interaction and Content Management (VAIG). He is vice-chair of the IAPR Technical Committee 14 Signal Analysis for Machine Intelligence. His research interests include computer vision, large-scale multimedia data mining and indexing (still and/or moving images), content-based retrieval, semantic labelling and annotation of multimedia content, multimodal fusion, and pattern recognition. He has co-authored over 120 papers in Books, Journals and International conferences. His current research interests include Multimedia Content Analysis, Mining and Indexing - Multimodal Fusion - Socially-Aware Multimedia.
