Multi attention module for visual tracking.

Boyu Chen,Peixia Li,Chong Sun,Dong Wang,Gang Yang,Huchuan Lu

Pattern Recognition（2019）

引用 70|浏览84

暂无评分

摘要

•The first tracker leverage multi-level visual attention.•Utilize LSTM to encode the video temporal information.•Make DNN-based tracking-by-detection more computationally feasible.•A promoting strategy for trackers with detection results.•Yield superior performance in two benchmark.

查看译文

关键词

Visual tracking,Deep neural network,Attention model,Long short term memory

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要