Datasets › LMOT

LMOT (Low-light Multi-object Tracking Dataset)

Introduced by Xinzhe Wang et al. in Multi-Object Tracking in the Dark10 May 2024 archive 2025-07-28

The Low-light Multi-object Tracking Dataset (LMOT) is a large-scale dataset that focuses on multi-object tracking in dark scenes. It consists of two parts: 1) The low-light and well-lit videos captured by our dual-camera system. 2) The real world low-light videos captured by a simple camera, to evaluate the generalization in real night scenarios. The videos are provided in both RAW format and sRGB format. After careful annotation, we collect 32 video sequences (2.3× MOT17), over 35K frames (3.1 × MOT17) and over 815K bounding boxes (2.8 × MOT17).

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 1 paper for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

No task tagged in the archive.

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • LMOT

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections