Sorry, you need to enable JavaScript to visit this website.

Summarization of Human Activity Videos Via Low-Rank Approximation

Citation Author(s):
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Submitted by:
Ioannis Mademlis
Last updated:
1 March 2017 - 6:25am
Document Type:
Document Year:
Presenters Name:
Ioannis Pitas
Paper Code:



Summarization of videos depicting human activities is a timely problem with important applications, e.g., in the domains of surveillance or film/TV production, that steadily becomes more relevant. Research on video summarization has mainly relied on global clustering or local (frame-by-frame) saliency methods to provide automated algorithmic
solutions for key-frame extraction. This work presents a method based on selecting as key-frames video frames able to optimally reconstruct the entire video. The novelty lies in modelling the reconstruction algebraically as a Column Subset Selection Problem (CSSP), resulting in extracting key-frames that correspond to elementary visual building
blocks. The problem is formulated under an optimization framework and approximately solved via a genetic algorithm. The proposed video summarization method is being evaluated using a publicly available annotated dataset and an objective evaluation metric. According to the quantitative results, it clearly outperforms the typical clustering approach.

0 users have voted:

Dataset Files

Summarization of Human Activity Videos Via Low-Rank Approximation