Datasets › UA-DETRAC

UA-DETRAC

Introduced by Longyin Wen et al. in UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking archive 2025-07-28

Consists of 100 challenging video sequences captured from real-world traffic scenes (over 140,000 frames with rich annotations, including occlusion, weather, vehicle category, truncation, and vehicle bounding boxes) for object detection, object tracking and MOT system.

Source: UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking

Image Source: UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

10 shown of 10 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 53. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Transformer-based assignment decision network for multiple object tracking 1 1 6 Aug 2022 not harvested
Video Sparse Transformer With Attention-Guided Memory for Video Object Detection 1 1 17 Jun 2022 not harvested
FFAVOD: Feature Fusion Architecture for Video Object Detection 1 1 15 Sep 2021 not harvested
RN-VID: A Feature Fusion Architecture for Video Object Detection 1 1 24 Mar 2020 not harvested
SpotNet: Self-Attention Multi-Task Network for Object Detection 1 1 13 Feb 2020 not harvested
Objects as Points 76 1 16 Apr 2019 ran 10 of 130 samples (120 unverified)
3D-DETNet: a Single Stage Video-Based Vehicle Detector 0 1 5 Jan 2018 not harvested
YOLO9000: Better, Faster, Stronger 231 1 25 Dec 2016 ran 16 of 60 samples (44 unverified; 22 pointer-only for licence)
R-FCN: Object Detection via Region-based Fully Convolutional Networks 48 1 20 May 2016 ran 1 of 11 samples (10 unverified)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 196 1 4 Jun 2015 ran 59 of 124 samples (65 unverified; 42 pointer-only for licence)

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • UA-DETRAC

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