模式识别系列讲座

Lecture Series in Pattern Recognition

题    目（TITLE）：Multiview techniques for 3DTV content description
讲 座 人（SPEAKER）：Prof. Ioannis Pitas；Aristotle University of Thessaloniki, Greece
主 持 人 (CHAIR)：Prof. Liang Wang
时    间 (TIME)：10:00AM, Sep 25 (Friday)
地    点 (VENUE)：The Second Meeting Room, 13th Floor

报告摘要（ABSTRACT）：

As 3DTV emerges, 3DTV content started already being accumulated in 3DTV broadcasters and 3D video production houses. Its volume will soon rise tremendously. Such content already started being posted in the web, as already done for 2D audiovisual material. Moreover, during the last two decades, we have witnessed an increasing research interest towards what one could call anthropocentric (human centered) video analysis, namely, algorithms that aim to extract, describe, and organize information regarding the basic element of most videos: humans. This diverse group of algorithms processes videos from various sources  and extracts a wealth of useful information related to the state (presence, identity, body posture, emotional state, etc.) and state transitions (body parts movements, activities, etc.) of individuals. The high level, semantic information derived from anthropocentric video analysis can be used for video content annotation and description which can then lead to efficient content search, indexing and retrieval. In this presentation we will review some anthropocentric video analysis algorithms, such as activity recognition and human or human body part detection that are applicable to either single-view or multiview video data.

报告人简介（BIOGRAPHY）：

Ioannis Pitas received the Diploma and PhD degree in Electrical Engineering, both from the Aristotle University of Thessaloniki, Greece. Since 1994, he has been a Professor at the Department of Informatics of the same University. He served as a Visiting Research Associate or Visiting Assistant Professor at several Universities. His current interests are in the areas of intelligent digital media, image/video processing (2D/3D) and human-centered interfaces. He has published over 658 papers, contributed in 38 books in his areas of interest and edited or (co-)authored another 8 books. He has also been an invited speaker and/or member of the program committee of several scientific conferences and workshops. In the past he served as Associate Editor or co-Editor of four international journals and General or Technical Chair of three international conferences (including ICIP2001). Heparticipated in 63 R&D projects, primarily funded by the European Union and is/was principal investigator/researcher in 39 such projects. He has 12600+ citations to his work and H-index 55+.

承办单位：模式识别国家重点实验室