Visual Tracking by TridenAlign and Context Embedding
Test code for "Visual Tracking by TridentAlign and Context Embedding"
ckpt_res18.tar
and ckpt_res50.tar
to ckpt/
folderTACT-18
and TACT-50
by modifying the cfgs/cfg_test.py
file (default: TACT-50
)cfgs/cfg_test.py
file to local LaSOTBenchmark
folder pathpython test_tracker.py
run_track_seq()
function in tracker_batch.py
, tracker can run on an arbitrary sequenceseq_name
: name of the given sequenceseq_path
: path to the given sequenceseq_imlist
: list of image file names of the given sequenceseq_gt
: ground truth box annotations of the given sequence (may only contain annotation for initial frame, [x_min,y_min,width,height]
format)If you find our work useful for your research, please consider citing the following paper:
@article{choi2020tact,
title={Visual tracking by tridentalign and context embedding},
author={Choi, Janghoon and Kwon, Junseok and Lee, Kyoung Mu},
journal={arXiv preprint arXiv:2007.06887},
year={2020}
}