Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching
CVPR(2020)
摘要
Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking, significantly much more research effort has been made in segmentation than tracking. In this paper, we introduce "tracking-by-detection" into VOS which can coherently integrate segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. Notably, our method is entirely online and thus suitable for one-shot learning, and our end-to-end trainable model allows multiple object segmentation in one forward pass. We achieve new state-of-the-art performance on the DAVIS benchmark without complicated bells and whistles in both speed and accuracy, with a speed of 0.14 second per frame and J&F measure of 75.9% respectively.
更多查看译文
关键词
image semantic segmentation,tracking-by-detection,integrates segmentation,temporal aggregation network,dynamic time-evolving template matching mechanism,end-to-end trainable model,multiple object segmentation,fast video object segmentation,dynamic template,video object tracking task,finest level,VOS task
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络