10 citations · 11 across the 3 of their papers we have counts for
5 papers
Revisiting Multi-Object Tracking Baselines: Hyperparameter Optimization with Multi-Fidelity Greedy Coordinate Search
Momir Adžemović
Multi-object tracking (MOT) is dominated by the tracking-by-detection paradigm, whose methods typically rely on a small set of hyperparameters that are conventionally chosen by han…
Learning Association via Track-Detection Matching for Multi-Object Tracking
Momir Adžemović
Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection…
Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art
Momir Adžemović
Multi-object tracking (MOT) is a core task in computer vision that involves detecting objects in video frames and associating them across time. The rise of deep learning has signif…
Engineering an Efficient Object Tracker for Non-Linear Motion
Momir Adžemović, Predrag Tadić, Andrija Petrović +1
The goal of multi-object tracking is to detect and track all objects in a scene while maintaining unique identifiers for each, by associating their bounding boxes across video fram…
Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking
Momir Adžemović, Predrag Tadić, Andrija Petrović +1
Traditional tracking-by-detection systems typically employ Kalman filters (KF) for state estimation. However, the KF requires domain-specific design choices and it is ill-suited to…