An image captioning dataset for military: Military Objects Dataset in Real Combat (MOCO)(Version 3.0)
School of Mechatronical Engineering, Beijing Institute of Technology
**Updated on July 1, 2024, the new version (Version 4.0) is waiting to be released.
| Dataset | Number of images | Number of captions |
|---|---|---|
| Train | 7192 | 35,960 |
| Test | 257 | 1,285 |
Our work provided the Military Objects In Real Combat (MOCO) dataset, which includes 7449 images with 37245 captions, and has the advantage of offering a rich set of captions for real military combat scenarios. This dataset is particularly beneficial for the research on military image captioning, as it provides a large and diverse collection of images accompanied by detailed captions. The open access nature of the MOCO dataset also ensures that it can be widely utilized by the research community, fostering innovation and collaboration in the field of military image analysis.
Out of ethical review requirements and to prevent the misuse of technology, this data can be accessed through application. Please be aware that the research purposes of the applicant will be rigorously reviewed to ensure that this data is not used for any improper purposes.
You can fill out the data usage application form and send it to the email [panlz_bit@hotmail.com].
This dataset is licensed under the MIT License Copyright (c) 2024 Panlizhi.
Please ensure you have read and understood the terms of the license before using the dataset. If you agree to comply with the MIT License, please proceed with using the dataset.
If you find the data presented herein useful for your research, please consider citing our article：Military Image Captioning for Low-altitude UAV or UGV Perspectives