Machine learning for video summarization
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.
Postgraduate
5 hours
Short Course
REGISTRATION: Free of charge
Both AIDA and non-AIDA students are encouraged to participate in this short course.
If you are an AIDA Student* already, please:
Step (a): Register in the course through its Web page.
AND
Step (b): Enroll in the same course in the AIDA system using the button below, so that this course enters your AIDA Certificate of Course Attendance.
If you are not an AIDA Student, do only step (a).
*AIDA Students should have been registered in the AIDA system already (they are PhD students or PostDocs that belong only to the AIDA Members listed in this page: Members)
16:00 to 21:30 CET
English
Online