Name
Abstract | ||
|---|---|---|
Existing deep siamese trackers are typically built on off-the-shelf CNN models for feature learning, with the demand for huge power consumption and memory storage. This limits current deep siamese trackers to be carried on resource-constrained devices like mobile phones, given factor that such a deployment normally requires cost-effective considerations. In this work, we address this issue by pres... |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICPR48806.2021.9412840 | 2020 25th International Conference on Pattern Recognition (ICPR) |
Keywords | DocType | ISSN |
Power demand,Pipelines,Memory management,Benchmark testing,Mobile handsets,Pattern recognition | Conference | 1051-4651 |
ISBN | Citations | PageRank |
978-1-7281-8808-9 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chengxin Liu | 1 | 0 | 2.37 |
| Zhiguo Cao | 2 | 314 | 44.17 |
| Wei Li | 3 | 436 | 140.67 |
| Yang Xiao | 4 | 237 | 26.58 |
| Shuaiyuan Du | 5 | 0 | 1.69 |
| Angfan Zhu | 6 | 0 | 1.35 |