Detail of the student project

List
Topic:Action recognition in long videos
Department:Katedra kybernetiky
Supervisor:Doc. Ing. Karel Zimmermann Ph.D.
Announce as:DP,BP,PMI,PRO
Description:The millions of cameras that are deployed every year generate a large amount of recorded, stored and transmitted video. In particular, a large proportion of this video depicts events about people, their activities, and behaviors. In order to effectively interpret this data, computer vision algorithms need the ability to understand and recognize human actions.

Web skolitele: http://cmp.felk.cvut.cz/~zimmerk/

Preffered qualification:
- B or better result achieved in a programming oriented subject or even better: the active participation in a programming competition (e.g. CTU Open Contest, ACM ICPC).
- B or better result achieved in a computer vision oriented subject.
- experience with Python and Tensorflow
- good mathemathical background.
Instruction:(1) Study state-of-the-art methods and publicly available implementations [1,2]
(2) Propose you own method.
Bibliography:[1] http://vision.stanford.edu/pdf/buch2017cvpr.pdf
[2] https://arxiv.org/pdf/1511.06984.pdf
Date:10.10.2017
Responsible person: Petr Pošík