An Efficient 3D CNN for Action/Object Segmentation in Video
This work addresses computational efficiency and performance in video segmentation tasks for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the challenge of high computational complexity in video object segmentation by proposing an end-to-end encoder-decoder 3D CNN that aggregates spatial and temporal information simultaneously, using 3D separable convolution to reduce operations while maintaining performance, and extends it to video action segmentation with an extra classifier, demonstrating superior performance on several datasets.
Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years. However, video object segmentation remains a challenging task due to its high computational complexity. Most of the previous methods employ a two-stream CNN framework to handle spatial and motion features separately. In this paper, we propose an end-to-end encoder-decoder style 3D CNN to aggregate spatial and temporal information simultaneously for video object segmentation. To efficiently process video, we propose 3D separable convolution for the pyramid pooling module and decoder, which dramatically reduces the number of operations while maintaining the performance. Moreover, we also extend our framework to video action segmentation by adding an extra classifier to predict the action label for actors in videos. Extensive experiments on several video datasets demonstrate the superior performance of the proposed approach for action and object segmentation compared to the state-of-the-art.