DOTA / xView
← Most-used data · All Remote sensing benchmarks datasets
Hyperspectral and aerial image collections used to compare classification and detection methods.
Tasks, access and usage conditions#
Mention counts below measure name matches in tracked papers, not benchmark quality or downloads. A family count can cover multiple datasets; it is not a separate count for each comparison row. Choose a task and version first, preserve evaluation splits, and follow the linked release terms. The site's content license does not replace the datasets' own terms.
| Dataset / version | Task and evaluation | Access and preparation | Usage conditions |
|---|---|---|---|
| DOTA 1.0 / 1.5 / 2.0 | Object detection in aerial images, including oriented bounding boxes. Evaluation: State oriented/horizontal-box task, IoU threshold, class set and patch merging; keep patches from the same scene in one split. | Official source / documentation Choose one release and its annotations/devkit; retain original large-image IDs when making patches. | Follow DOTA’s release agreement and source-image conditions; evaluation-code licensing does not itself license every image. |
| xView 2018 | Overhead-image object detection with fine-grained object categories. Evaluation: Use the official class mapping and evaluation protocol; compare like-for-like box definitions and image resolutions. | Official source / documentation Use the official challenge registration/download route and its annotations; confirm present account access. | Accept the official dataset/challenge terms, including source-imagery restrictions; do not assume that DOTA terms apply. |
Key findings#
- From Nov 2023 to Oct 2026, 42 archived papers mentioned DOTA / xView in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Jan 2025 (4).
- No paper of the tracked journals mentioned DOTA / xView in the last 30 days (2026-10-07 to 2026-11-05).
- From 2017 to 2026 (so far), DOTA / xView was mentioned in 61 papers in the tracked journals, most of them in AI (61).
- 16 of them were published in 2025, against 0 in 2017.
- Since 2023, the institutions with the most of these papers were University of Chinese Academy of Sciences (5), Wuhan University (5) and Chinese Academy of Sciences (3).
- The journals publishing most of them were IEEE Transactions on Pattern Analysis and Machine Intelligence (9), Pattern Recognition (7) and Expert Systems with Applications (5).
- The most-cited of them is “Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges” (IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021), with 681 citations.
- Papers use DOTA / xView most often with ImageNet (14), MS COCO (12) and Kaggle (5); it has 11 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.
Mentions over 36 months#
| Trend | Nov 23–Oct 24 | Nov 24–Oct 25 | Nov 25–Oct 26 | 36 months |
|---|---|---|---|---|
| 11 | 17 | 14 | 42 |
Papers per year#
| Category | 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026 (so far) |
|---|---|---|---|---|---|---|---|---|---|---|
| AI | 0 | 0 | 0 | 1 | 3 | 8 | 8 | 13 | 16 | 12 |
| All categories | 0 | 0 | 0 | 1 | 3 | 8 | 8 | 13 | 16 | 12 |
Where the papers come from#
| # | Journal | Papers |
|---|---|---|
| 1 | IEEE Transactions on Pattern Analysis and Machine Intelligence | 9 |
| 2 | Pattern Recognition | 7 |
| 3 | Expert Systems with Applications | 5 |
| 4 | Artificial Intelligence Review | 4 |
| 5 | Neural Computing and Applications | 4 |
| 6 | Neural Networks | 3 |
| 7 | International Journal of Computer Vision | 3 |
| 8 | Image and Vision Computing | 2 |
| 9 | Applied Intelligence | 2 |
| 10 | Knowledge-Based Systems | 2 |
| # | Institution | Papers |
|---|---|---|
| 1 | University of Chinese Academy of Sciences | 5 |
| 2 | Wuhan University | 5 |
| 3 | Chinese Academy of Sciences | 3 |
| 4 | Nankai University | 3 |
| 5 | Northwestern Polytechnical University | 3 |
| 6 | State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing | 3 |
| 7 | Chang'an University | 2 |
| 8 | Harbin Institute of Technology | 2 |
| 9 | Huawei Technologies (China) | 2 |
| 10 | Huazhong University of Science and Technology | 2 |
| # | Country | Papers |
|---|---|---|
| 1 | China | 36 |
| 2 | United States | 4 |
| 3 | India | 3 |
| 4 | Singapore | 2 |
| 5 | United Arab Emirates | 1 |
| 6 | Australia | 1 |
| 7 | Bangladesh | 1 |
| 8 | Egypt | 1 |
| 9 | Spain | 1 |
| 10 | France | 1 |
| # | Keyword | Papers |
|---|---|---|
| 1 | DOTA | 14 |
| 2 | object detection | 11 |
| 3 | oriented object detection | 7 |
| 4 | remote sensing images | 7 |
| 5 | aerial images | 6 |
| 6 | remote sensing object detection | 6 |
| 7 | small object detection | 6 |
| 8 | HRSC2016 | 5 |
| 9 | semantic segmentation | 5 |
| 10 | DOTA dataset | 4 |
Most-cited papers#
Used together with#
| Used with | Type | Papers using both | Lift |
|---|---|---|---|
| ImageNet | Dataset | 14 | 4.7 |
| MS COCO | Dataset | 12 | 10.1 |
| Kaggle | Dataset | 5 | 6.8 |
| KITTI | Dataset | 5 | 8.7 |
| PASCAL VOC | Dataset | 5 | 11.8 |
| Scene classification (NWPU-RESISC45, UC Merced, AID) | Dataset | 5 | 81.7 |
| ADE20K | Dataset | 3 | 16.7 |
| CIFAR-10 / CIFAR-100 | Dataset | 3 | 1.7 |
| nuScenes / Waymo Open / Argoverse | Dataset | 3 | 8.0 |
| Skeleton and pose (NTU RGB+D, Human3.6M) | Dataset | 3 | 14.7 |
| ultralytics/ultralytics | Code repository | 3 | 12.7 |
Cite this page
Scholar4AI. (2026). DOTA / xView. Journal and Conference Research Rankings. Retrieved November 5, 2026, from https://scholar4ai.com/datasets/dota-xview
@misc{scholar4ai-datasets-dota-xview,
author = {{Scholar4AI}},
title = {DOTA / xView},
year = {2026},
howpublished = {\url{https://scholar4ai.com/datasets/dota-xview}},
urldate = {2026-11-05},
note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}