Details

Autor(en) / Beteiligte

• Guo, Dongyan
• Shao, Yanyan
• Cui, Ying
• Wang, Zhenhua
• Zhang, Liyan
• Shen, Chunhua

Titel

Graph Attention Tracking

Ist Teil von

• 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, p.9538-9547

Ort / Verlag

IEEE

Erscheinungsjahr

2021

Link zum Volltext

Quelle

IEL

Beschreibungen/Notizen

• Siamese network based trackers formulate the visual tracking task as a similarity matching problem. Almost all popular Siamese trackers realize the similarity learning via convolutional feature cross-correlation between a target branch and a search branch. However, since the size of target feature region needs to be pre-fixed, these cross-correlation base methods suffer from either reserving much adverse background information or missing a great deal of foreground information. Moreover, the global matching be-tween the target and search region also largely neglects the target structure and part-level information.In this paper, to solve the above issues, we propose a simple target-aware Siamese graph attention network for general object tracking. We propose to establish part-to-part correspondence between the target and the search region with a complete bipartite graph, and apply the graph attention mechanism to propagate target information from the template feature to the search feature. Further, instead of using the pre-fixed region cropping for template-feature-area selection, we investigate a target-aware area selection mechanism to fit the size and aspect ratio variations of different objects. Experiments on challenging benchmarks including GOT-10k, UAV123, OTB-100 and LaSOT demonstrate that the proposed SiamGAT outperforms many state-of-the-art trackers and achieves leading performance. Code is available at: https://git.io/SiamGAT