Multi attention module for visual tracking

Open Webpage

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

Published: 01 Jan 2019, Last Modified: 13 Nov 2024Pattern Recognit. 2019EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•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.