Data · dataset · 2026
UAVREL: A Benchmark Dataset for Dynamic Relation Comprehension in UAV Videos
Listed in ScienceDB
Description
Serious declaration: If this dataset is used in papers, books, academic reports, or other works, please cite the following data paper references: Liu Xiaorui, Deng Chubo, Hou Zhongyan, Yan Qiwei, Lu Wanxuan, Hou Yingyan, Yu Hongfeng, Sun Xian UAVREL: UAV Video Dynamic Relationship Understanding Benchmark Dataset [J]. Journal of Electronics and Information Technology, 2026 LIU Xiaorui, DENG Chubo, HOU Zhongyan, YAN Qiwei, LU Wanxuan, HOU Yingyan, YU Hongfeng, SUN Xian.
UAVREL: A Benchmark Dataset for Dynamic Relation Comprehension in UAV Videos[J]. Journal of Electronics & Information Technology, 2026. Authors: Liu Xiaorui, Deng Chubo, Hou Zhongyan, Yan Qiwei, Lu Wanxuan, Hou Yingyan, Yu Hongfeng, Sun Xian Unit: Aerospace Information Innovation Institute, Chinese Academy of Sciences Corresponding author: Deng Chubo, email: dengcb@aircas.ac.cn Fund
Read the rest (3 more)
Project
National Natural Science Foundation of China Youth Science Fund 42301437 Dataset Introduction: Video scene graph generation is an advanced visual understanding task that extracts objects and their interrelationships from videos. At present, relevant research mostly focuses on natural scenes, and further exploration is still needed in the field of remote sensing. The significant changes in the perspective of drone videos and the large differences in target scales have significantly increased the cost of data annotation, and the lack of large-scale benchmark datasets is the main obstacle to current research on drone video scene graph generation.
We constructed a dataset for understanding drone video relationships, annotating 12 target categories and approximately 880000 target boxes in 50 drone videos; And based on the target box, about 460000 relationship triplets were annotated for 20 relationship categories.
Links
Where it is published
- DOI doi.org/10.57760/sciencedb.j00173.00099 ↗
DOI / persistent id · from scidb cn
Catalogue records · 1
- OAI-PMH record scidb.cn/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.57760%2… ↗
metadata API · from scidb cn
Topics
- From keywords
- Earth & Environmental Science · Engineering · Humanities · Life Sciences · Social Science
- Inferred from text
- Design 71% · Satellite remote sensing 65% · Video 75%
Provenance · 1 source records, 13 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| ScienceDB | 10.57760/sciencedb.j00173.00099 | 10 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].anzsrc:group:3303 | enrichment · scidb cn | taxonomy-embedding@1.0.0 | title+keywords+description (71%) |
| concepts[field].local:field:earth-environmental | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:engineering | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:humanities | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:social-science | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[modality].local:modality:remote-sensing | enrichment · scidb cn | keyword-concept-rules@1.0.0 | title+description (65%) |
| concepts[modality].local:modality:video | enrichment · scidb cn | keyword-concept-rules@1.0.0 | title+description (75%) |
| description | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/description |
| license | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/rights |
| publication_date | source · scidb cn | connector:scidb_cn@1.0.0 | |
| title | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/title |