The benefits of synthetic data for action categorization
share
In this paper, we study the value of using synthetically produced videos as training data for neural networks used for action categorization. Motivated by the fact that texture and background of a video play little to no significant roles in optical flow, we generated simplified texture-less and background-less videos and utilized the synthetic data to train a Temporal Segment Network (TSN). The results demonstrated that augmenting TSN with simplified synthetic data improved the original network accuracy (68.5 when adding 4,000 videos and 72.4 using simplified synthetic videos alone on 25 classes of UCF-101 achieved 30.71 Finally, results showed that when reducing the number of real videos of UCF-25 to 10 85.41
READ FULL TEXT