LaSOT: Large-scale Single Object Tracking

Download Webpage    

---

Note 1: The official website of LaSOT can be found here. This webpage only provides download links, as a backup, in case that the download links in the official website are invalid.

Note 2: OneDrive is recommended to download the data. The data on the Google Drive may not be stable.

---

Download videos of converence version (70 categories with 1,400 videos, ~227G):

• Sequences of all categories from three sources (MD5: 2f9fb392c6e2ce0192bba0d531703e2d)
  • OneDrive
  • Google Drive part-1   Google Drive part-2   Google Drive part-3
  • Baidu Pan


• Sequences of each category (MD5)
  • OneDrive
  • Baidu Pan


• Sequences of Testing set only (MD5: a9038384fd94d30e7ad6a1b7cf32ec73)
  • Not provided (please download the whole dataset and refer to Testing Subset)

---

Download videos of the new subset in extended journal version (15 categories with 150 videos, ~59G):

• Sequences of all categories (SHA1: 27F62B85A66844F91CEB2196F39A653FFB158224)
  • OneDrive
  • Google Drive
  • Local


• Sequences of each category (SHA1)
  • OneDrive

---

Evaluation:

• Toolkit
  • Conference version - Google Drive or Github
  • Journal version (it also supports conference version) - Google Drive


• Protocol
  • Protocol I (no constraint): All 1,400 sequences in LaSOT (note: conference version) are employed for evaluation.
  • Protocol II (full-overlap): Only 280 sequences in the testing subset (note: conference version) of LaSOT are utilized for evaluation. (Training/Testing split: Training Subset | Testing Subset)
  • Protocol III (one-shot): Only 150 sequences in the newly collected extension subset (note: journal version) of LaSOT are utilized for evaluation. (Training/Testing split: Training Subset | Testing Subset)

---

Reference

• LaSOT: A High-quality Large-scale Single Object Tracking Benchmark
  H. Fan*, H. Bai*, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, Harshit, M. Huang, J Liu, Y. Xu, C. Liao, L Yuan, and H. Ling
  International Journal of Computer Vision (IJCV), 129: 439–461, 2021.


• LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking
  H. Fan*, L. Lin*, F. Yang*, P. Chu*, G. Deng, S. Yu, H. Bai, Y. Xu, C. Liao, and H. Ling
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

---