ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition
This work addresses a domain-specific problem for action recognition researchers by providing an incremental improvement over existing augmentation techniques.
The paper tackles the lack of tailored data augmentation methods for action recognition by proposing ObjectMix, which combines object regions from two videos using instance segmentation to create new videos, achieving superior performance over VideoMix on UCF101 and HMDB51 datasets.
In this paper, we propose a data augmentation method for action recognition using instance segmentation. Although many data augmentation methods have been proposed for image recognition, few of them are tailored for action recognition. Our proposed method, ObjectMix, extracts each object region from two videos using instance segmentation and combines them to create new videos. Experiments on two action recognition datasets, UCF101 and HMDB51, demonstrate the effectiveness of the proposed method and show its superiority over VideoMix, a prior work.