LaSOT

The LaSOT dataset is a large-scale benchmark for visual tracking, containing 1400 video sequences with varying difficulties.

Data and Resources

Cite this as

H. Fan, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, H. Bai, Y. Xu, C. Liao, H. Ling (2024). Dataset: LaSOT. https://doi.org/10.57702/qivyutb1

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2009.14635
Citation
  • https://doi.org/10.48550/arXiv.2108.13962
  • https://doi.org/10.1109/TIP.2021.3130533
  • https://doi.org/10.48550/arXiv.1912.08531
  • https://doi.org/10.48550/arXiv.2407.05235
  • https://doi.org/10.48550/arXiv.1911.07959
Author H. Fan
More Authors
L. Lin
F. Yang
P. Chu
G. Deng
S. Yu
H. Bai
Y. Xu
C. Liao
H. Ling
Homepage https://github.com/CSAILVision/LaSOT