论文标题
合成数据对行动分类的好处
The benefits of synthetic data for action categorization
论文作者
论文摘要
在本文中，我们研究了使用合成产生的视频作为用于行动分类的神经网络的培训数据的价值。由于视频的纹理和背景在光流中扮演的角色几乎没有重要的角色，因此我们生成了简化的无纹理和无背景的视频，并利用合成数据来训练时间段网络（TSN）。结果表明，通过简化的合成数据增强TSN提高了原始网络的准确性（68.5％），在添加4,000个视频时，HMDB-51的HMDB-51在添加8,000个视频时可获得71.8％的速度。此外，在接受2500个视频培训时，仅使用简化的25类UCF-101类的培训就可以达到30.71％，而在5000个视频中接受培训时，培训可实现52.7％。最后，结果表明，当将UCF-25的真实视频数量减少至10％并将其与合成视频相结合时，准确度下降到仅为85.41％，而当未添加合成数据时，降至77.4％。
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%), achieving 71.8% on HMDB-51 when adding 4,000 videos and 72.4% when adding 8,000 videos. Also, training using simplified synthetic videos alone on 25 classes of UCF-101 achieved 30.71% when trained on 2500 videos and 52.7% when trained on 5000 videos. Finally, results showed that when reducing the number of real videos of UCF-25 to 10% and combining them with synthetic videos, the accuracy drops to only 85.41%, compared to a drop to 77.4% when no synthetic data is added.
