How To Train Your Deep Multi-Object Tracker

The recent trend in vision-based multi-object tracking (MOT) is heading towards leveraging the representational power of deep learning to jointly learn to detect and track objects. However, existing methods train only certain sub-modules using loss functions that often do not correlate with established tracking evaluation measures such as Multi-Object Tracking Accuracy (MOTA) and Precision (MOTP)... (read more)

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Multi-Object Tracking 2D MOT 2015 DeepMOT-Tracktor MOTA 44.1 # 3
Multi-Object Tracking MOT16 DeepMOT-Tracktor MOTA 54.8 # 5
Multi-Object Tracking MOT17 DeepMOT-Tracktor MOTA 53.7 # 4

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet