</> Code with Papers by Syntology

Datasets › UAV-Human

UAV-Human

Introduced by Tianjiao Li et al. in UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles2 Apr 2021 archive 2025-07-28

UAV-Human is a large dataset for human behavior understanding with UAVs. It contains 67,428 multi-modal video sequences and 119 subjects for action recognition, 22,476 frames for pose estimation, 41,290 frames and 1,144 identities for person re-identification, and 22,263 frames for attribute recognition. The dataset was collected by a flying UAV in multiple urban and rural districts in both daytime and nighttime over three months, hence covering extensive diversities w.r.t subjects, backgrounds, illuminations, weathers, occlusions, camera motions, and UAV flying attitudes. This dataset can be used for UAV-based human behavior understanding, including action recognition, pose estimation, re-identification, and attribute recognition.

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 5 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.

First row (archive order)PaperCode
Skeleton Based Action Recognition UAV-Human HDBN CSv1(%) 47.96 HDBN: A Novel Hybrid Dual-branch Network for Robust... liujf69/icmew2024-track10 9 Compare
Action Recognition UAV-Human PMI Sampler Top 1 Accuracy 55.0 PMI Sampler: Patch Similarity Guided Frame Selection for... ricky-xian/pmi-sampler 4 Compare
Person Re-Identification UAV-Human DG-Net Rank-1 65.81 Joint Discriminative and Generative Learning for Person... layumi/Person_reID_baseline_pytorch +11 4 Compare
Pedestrian Attribute Recognition UAV-Human DenseNet Backpack 63.9 Densely Connected Convolutional Networks pytorch/vision +145 2 Compare
Pose Estimation UAV-Human AlphaPose mAP 56.9 RMPE: Regional Multi-person Pose Estimation MVIG-SJTU/AlphaPose +13 2 Compare

Papers archive 2025-07-28

21 shown of 21 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 47. 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
HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition 1 1 24 Apr 2024 not harvested
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities 1 1 28 Dec 2023 not harvested
Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition 1 1 12 May 2023 not harvested
Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition 1 1 1 May 2023 not harvested
PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition 1 1 14 Apr 2023 not harvested
MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition 1 1 5 Mar 2023 not harvested
AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning 0 1 2 Mar 2023 not harvested
FAR: Fourier Aerial Video Recognition 1 1 21 Mar 2022 not harvested
HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction 0 1 1 Aug 2020 not harvested
Skeleton-Based Action Recognition With Shift Graph Convolutional Network 1 1 1 Jun 2020 not harvested
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation 19 1 27 Aug 2019 ran 5 of 27 samples (22 unverified)
Skeleton-Based Action Recognition With Directed Graph Neural Networks 1 1 1 Jun 2019 not harvested
Joint Discriminative and Generative Learning for Person Re-identification 12 1 15 Apr 2019 ran 3 of 19 samples (16 unverified)
Bag of Tricks and A Strong Baseline for Deep Person Re-identification 8 1 17 Mar 2019 ran 2 of 8 samples (6 unverified)
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition 4 1 20 May 2018 not harvested
Part-Aligned Bilinear Representations for Person Re-identification 0 1 19 Apr 2018 not harvested
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition 24 1 23 Jan 2018 ran 2 of 2 samples (0 unverified)
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline) 29 1 26 Nov 2017 not harvested
RMPE: Regional Multi-person Pose Estimation 14 1 1 Dec 2016 not harvested
Densely Connected Convolutional Networks 146 1 25 Aug 2016 ran 18 of 71 samples (53 unverified; 7 pointer-only for licence)
Deep Residual Learning for Image Recognition 484 1 10 Dec 2015 ran 230 of 377 samples (147 unverified; 187 pointer-only for licence)

Dataset loaders archive 2025-07-28

SUTDCV/UAV-Human

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

Tasks archive 2025-07-28

Pose EstimationAction RecognitionPerson Re-Identification3D Action Recognition2D Human Pose EstimationSkeleton Based Action RecognitionPedestrian Attribute Recognition

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

RGB-DRGB Video

Languages archive 2025-07-28

English

Variants archive 2025-07-28

  • UAV-Human

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