Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers

Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers. Meanwhile, most deep learning models are known to be vulnerable to adversarial examples that are crafted with small perturbations but could mislead the model prediction.

Data and Resources

Cite this as

Delv Lin, Qi Chen, Chengyu Zhou, Kun He (2024). Dataset: Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers. https://doi.org/10.57702/sky41cvt

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.2111.08954
Author Delv Lin
More Authors
Qi Chen
Chengyu Zhou
Kun He
Homepage https://github.com/JHL-HUST/TraSw