MOT-17

The MOT-17 dataset is a benchmark for evaluating multi-object tracking algorithms, containing video sequences with annotated object trajectories and identities, specifically designed to assess performance in scenarios with challenges like occlusion.

Papers using MOT-17 (12)

No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyond2025 · 3 citesStableTrack: Stabilizing Multi-Object Tracking on Low-Frequency Detections2025FusionSORT: Fusion Methods for Online Multi-object Visual Tracking2025YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID2025TransTrack: Multiple Object Tracking with Transformer2020 · 360 citesDeep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification2023 · 267 citesMultiple People Tracking Using Hierarchical Deep Tracklet Re-identification2018 · 21 citesDeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions2023 · 9 citesContrastive Learning for Multi-Object Tracking with Transformers2023 · 4 citesTracking Objects as Pixel-wise Distributions2022 · 1 citesEnd-to-End Multi-Object Tracking with Global Response Map2020Learning Data Association for Multi-Object Tracking using Only Coordinates2024