Datasets › LMOT
LMOT (Low-light Multi-object Tracking Dataset)
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\times MOT17), over 35K frames (3.1 \times MOT17) and over 815K bounding boxes (2.8 \times 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