1 Hit in 3.1 sec

1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking [article]

Fei Du, Bo Xu, Jiasheng Tang, Yuqi Zhang, Fan Wang, Hao Li
2021 arXiv   pre-print
Then we learned appearance features to represent any object by training feature learning networks. We ensemble several models for improving detection and feature representation.  ...  We extend the classical tracking-by-detection paradigm to this tracking-any-object task. Solid detection results are first extracted from TAO dataset.  ...  for any category of objects.  ... 
arXiv:2101.08040v2 fatcat:myvig7rmaffkxp52dvg5f2kerq