Comparative Analysis: Violence Recognition from Videos using Transfer Learning
This work addresses violence detection in videos, a complex and less-investigated problem in computer vision, but it is incremental as it focuses on benchmarking and data scaling without introducing new methods.
The study tackled violence recognition in videos by benchmarking deep learning techniques on a complex dataset and testing the impact of increasing data volume, finding that expanding the dataset from 500 to 1,600 videos improved average accuracy by 6% across four models.
Action recognition has become a hot topic in computer vision. However, the main applications of computer vision in video processing have focused on detection of relatively simple actions while complex events such as violence detection have been comparatively less investigated. This study focuses on the benchmarking of various deep learning techniques on a complex dataset. Next, a larger dataset is utilized to test the uplift from increasing volume of data. The dataset size increase from 500 to 1,600 videos resulted in a notable average accuracy improvement of 6% across four models.