DESCRIPTION

Video summarization is the problem of automatically selecting important key-shots and/or key-frames from an input video, in order to construct a brief summary of the original sequence, capturing its essential content. Both supervised and unsupervised machine learning methods have been employed for solving video summarization tasks, ranging from simple video frame clustering to sophisticated deep learning approaches. It is a task of immense practical importance to media and WWW professionals, since it allows them (or remote users) to browse through endless hours of filmed footage without having to actually watch the entire content. Video summarization is highly significant in automation solutions for TV/movie production, video surveillance, sports coverage, media archiving, etc. This short course will present the various types of video summaries and the most important families of learning algorithms that been developed over the years to tackle video summarization, focusing on the prominent problem of key-frame extraction. The short course is composed of two consecutive 2.5-hour lectures, covering pre-deep learning and purely neural methods, respectively. A 30-minute coffee break will intercede between them.

WHEN?

The course will take place on 28 June 2022.

WHERE?

All lectures and workshops will be delivered remotely.

The course link is the following: https://authgr.zoom.us/j/96520795754

PROGRAM

Time*/date 28/06/2022
16:00-21:30 Machine learning for video summarization

*Central European Summer Time (CEST)

————————————————————————————————————————————————————————-

REGISTRATION

————————————————————————————————————————————————————————-

Free to anyone.

Register

 


Lectures will be in English. PDF slides will be available to course attendees.

————————————————————————————————————————————————————————-

LECTURERS

Lecturer name & affiliation: Ioannis Mademlis, imademlis@csd.auth.gr, Aristotle University of Thessaloniki, Artificial Intelligence and Information Analysis Laboratory (AIIA)

Dr. Ioannis Mademlis is a computer scientist, specialized in artificial intelligence. He received a M.Sc. degree in intelligent/cognitive systems (2014) and a Ph.D. in machine learning and computer vision (2018), both from the Aristotle University of Thessaloniki, Greece (AUTH). While pursuing his Ph.D., he was granted a 1-year academic excellence scholarship. Presently, he is employed as a postdoctoral research associate at AUTH. He has participated in 5 European Union-funded R&D projects, having co-authored more than 45 publications in academic journals and international conferences. His current research interests include machine learning, computer vision, natural computing, autonomous robotics and intelligent cinematography.

AUDIENCE

Postgraduate. Any engineer, practicing scientist or student with computer vision/machine learning background and interests.

IF I HAVE A QUESTION?

Feel free to contact us for any further information with email to Ioanna Koroni (koroniioanna@csd.auth.gr) with subject “Machine learning for video summarization”.