MOT20

Overview edit

Variants: MOT20

Associated Benchmarks

This dataset is used in 1 benchmark:

• Multi-Object Tracking - Metrics: HOTA, MOTA, IDF1, AssA, Speed (FPS)

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• HopTrack: A Real-time Multi-Object Tracking System for Embedded Devices (2024) -
• When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking (2024) -
• One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation (2024) -
• BoostTrack++: using tracklet information to detect more objects in multiple object tracking (2024) -
• SFSORT: Scene Features-based Simple Online Real-Time Tracker (2024) -
• UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation (2023) -
• SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth (2023) -
• Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification (2023) -
• SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking (2022) -
• Multiple Object Tracking from appearance by hierarchically clustering tracklets (2022) -
• BoT-SORT: Robust Associations Multi-Pedestrian Tracking (2022) -
• Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker (2022) -
• Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking (2022) -
• SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking (2022) -
• StrongSORT: Make DeepSORT Great Again (2022) -
• Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation (2022) -
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box (2021) -
• TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking (2021) -
• TransCenter: Transformers with Dense Representations for Multiple-Object Tracking (2021) -
• Joint Object Detection and Multi-Object Tracking with Graph Neural Networks (2020) -