Authors
Botao Ye, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen
Publication date
2022/10/23
Book
European Conference on Computer Vision
Pages
341-357
Publisher
Springer Nature Switzerland
Description
The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-background discriminability. To tackle the above issue, we propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling by bridging the template-search image pairs with bidirectional information flows. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. Since no extra heavy relation modeling module is needed and the implementation is highly parallelized, the proposed tracker runs at a fast speed. To further improve the inference efficiency, an in-network candidate early elimination module is proposed based on the strong similarity prior calculated in the one-stream …
Total citations
Scholar articles
B Ye, H Chang, B Ma, S Shan, X Chen - European Conference on Computer Vision, 2022