Abstract | ||
---|---|---|
Recently, deep Siamese network-based trackers have achieved superior performance in the visual tracking community. Siamese trackers formulate the visual tracking problem as learning the similarity metric by cross-correlation between the target template and the search region. However, previous Siamese trackers are still susceptible to the distractors, mainly due to two reasons: (1)template region contains non-target information; (2)insufficient distractor learning in template frame. In this paper, we comprehensively combine the ROI align pooling with the Siamese Network (named R-SiamNet). Due to accurate region pooling operator, we present simple yet effective multi-distractors learning for template, which imposes the discriminative of feature embedding. The experimental results show that our R-SiamNet outperforms the state-of-the-art trackers on VOT2016 [1], VOT2018 [2] and OTB100 [3] datasets. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/MIPR49039.2020.00012 | 2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) |
Keywords | DocType | ISBN |
Siamese-Tracking,ROI Operater,Feature Alignment,Multi-Distractors Learning | Conference | 978-1-7281-4273-9 |
Citations | PageRank | References |
0 | 0.34 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lihui Su | 1 | 0 | 0.34 |
Yaowei Wang | 2 | 134 | 29.62 |
Yonghong Tian | 3 | 1057 | 102.81 |