2020
DOI: 10.1007/s11263-020-01387-y
|View full text |Cite
|
Sign up to set email alerts
|

LaSOT: A High-quality Large-scale Single Object Tracking Benchmark

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

2
488
0
1

Year Published

2020
2020
2022
2022

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 289 publications
(501 citation statements)
references
References 82 publications
2
488
0
1
Order By: Relevance
“…Then, ablation study is presented to analyze the effects of each component in the proposed tracker. Furthermore, the experimental results of HROM are compared on several popular tracking benchmarks including OTB2015 [ 28 ], UAV123 [ 51 ], VOT2018 [ 52 ] and LaSOT [ 53 ] with the state-of-the-art tracking algorithms.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Then, ablation study is presented to analyze the effects of each component in the proposed tracker. Furthermore, the experimental results of HROM are compared on several popular tracking benchmarks including OTB2015 [ 28 ], UAV123 [ 51 ], VOT2018 [ 52 ] and LaSOT [ 53 ] with the state-of-the-art tracking algorithms.…”
Section: Methodsmentioning
confidence: 99%
“…LaSOT [ 53 ] is a recent released more challenging benchmark for object tracking, and provides a high-quality and large-scale dense annotations with a total of 1400 sequences and 280 sequences for testing. Specifically, it includes 70 categories and each one contains 20 videos.…”
Section: Methodsmentioning
confidence: 99%
“…Then, we conduct ablation studies from two perspectives: 1) evaluate the impact of the size of long-term memory sample set on the performance of the model; 2) compare and analyze the important role of the update method of long-term memory sample set on the model. Finally, we evaluate our method on a large-scale longterm benchmark dataset LaSOT [36].…”
Section: Methodsmentioning
confidence: 99%
“…It was followed by the more recent Templeā€Colour [26] and DTB70 [27] datasets, while the former focus on colour videos and the latter collects the videos from UAV or drone. Recently, larger tracking datasets have also been proposed [28, 29]. The VOT [30, 31] challenge updates its dataset yearly, with its own evaluation metrics.…”
Section: Related Workmentioning
confidence: 99%