Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.
We extend the classical tracking-by-detection paradigm to this tracking-any-object task.
Ranked #1 on Multi-Object Tracking on TAO (using extra training data)
Furthermore, we can show that the metric is learned from latent examples only, but it can preserve the large margin property even for the original data.
Hence, we propose to learn the model and the adversarial distribution simultaneously with the stochastic algorithm for efficiency.