模式识别学术讲座

Lecture Series in Pattern Recognition  

题    目（TITLE）：Visual Contents Analysis at Lincoln

讲 座 人（SPEAKER）: Amr Ahmed (University of Lincoln, UK)

主 持 人 (CHAIR)：Cheng-Lin Liu

时    间 (TIME)：10:00AM, September 13th

地    点 (VENUE)： No.2 Meeting Room, Intelligence Bld

报告摘要（ABSTRACT）：

In this talk, I will first start with a brief introduction to the visual contents analysis and especially video analysis and annotation. Then, I’ll present some of our recent work on video annotation and video similarity on compressed and uncompressed domains. This will include the utilisation of common-sense knowledge basis with computer vision for semantic video annotation and the work on thumbnail-size images/frames for video similarity that helps in various aspects including the content-based retrieval. Finally, some current and forthcoming research topics will be mentioned.

报告人简介（BIOGRAPHY）：

Amr is a research active academic in the School of Computer Science, University of Lincoln, UK. He received his B.Sc. degree in Electrical Engineering and M.Sc. (by Research) degree in Computer Systems (online Handwriting Recognition for Arabic) from Ain Shams University, Cairo Egypt, in 1993 and 1999 respectively. Then, he received his Ph.D. degree in 3D Graphics and motion synthesis from the University of Surrey, UK, in 2004.  Before joining Lincoln, Amr worked with Sharp Labs of Europe (SLE at Oxford, UK) as a Research Scientist, working on video shot-boundary detection for one of Sharp’s digital TV products. Then, he was a postdoctoral Research Fellow responsible for the REVEAL project (Extracting Video Evidence and constructing visual Thesaurus from CCTV recordings) at the University of Surrey. In Lincoln, he founded the DCAPI (Digital Contents Analysis, Production and Interaction) research group, which he is leading since then.

His research interest is currently focused on Digital Contents Analysis, (including semantic analysis). This includes (but not limited to) Video/Image Understanding, Video/Image Annotation, Scene Understanding, Semantic Analysis, Blog analysis and Data mining. Previous research (which is still of interest) include Handwriting recognition (especially in Arabic), 3D Graphics and  Virtual/Augmented Reality.

Amr is a member of Editorial Board, Program Committee, and/or reviewer for a number of international Journals and Conferences, including IEEE Transaction on Multimedia, IEEE Transaction on Systems, Man, and Cybernetics, Signal Processing Journal (Elsevier), International Journal of Image and Graphics (World Scientific), EURASIP Journal on Image and Video Processing, Neurocomputing Journal (Elsevier) and BMVC (British Machine Vision) Conference.