DanceTrack

Dataset Card for DanceTrack DanceTrack is a multi-human tracking dataset with two emphasized properties, (1) uniform appearance: humans are in highly similar and almost undistinguished appearance, (2) diverse motion: humans are in complicated motion pattern and their relative positions exchange frequently. We expect the combination of uniform appearance and complicated motion pattern makes DanceTrack a platform to encourage more comprehensive and intelligent multi-object tracking… See the full description on the dataset page: https://huggingface.co/datasets/Voxel51/DanceTrack.

Papers using DanceTrack (12)

Dancetrack: Multi-object Tracking In Uniform Appearance And Diverse Motion2021 · 314 citesMemotr: Long-term Memory-augmented Transformer For Multi-object Tracking2023 · 100 citesDeep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification2023 · 10 citesMotrv2: Bootstrapping End-to-end Multi-object Tracking By Pretrained Object Detectors2022 · 9 citesSimple Cues Lead To A Strong Multi-object Tracker2022 · 6 citesMultiple Object Tracking Challenge Technical Report For Team Mt_iot2022 · 3 citesDeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions2023Learning Data Association for Multi-Object Tracking using Only Coordinates2024When To Extract Reid Features: A Selective Approach For Improved Multiple Object Tracking2024Occlusion-aware SORT: Observing Occlusion For Robust Multi-object Tracking2026Temporally Propagated Masks And Bounding Boxes: Combining The Best Of Both Worlds For Multi-object Tracking2024Motion-aware Transformer For Multi-object Tracking2025