JUHE API Marketplace
Back to datasets
Dataset assetOpen Source CommunityImage ProcessingRemote Sensing Technology

LEVIR-CC Dataset

The LEVIR‑CC dataset is a large dataset for remote‑sensing image change caption generation, specifically supporting research on change captioning using dual‑branch Transformers.

Source
github
Created
Apr 26, 2022
Updated
May 11, 2024
Signals
508 views
Availability
Linked source ready
Overview

Dataset description and usage context

Dataset Overview

Dataset Name

  • LEVIR‑CC Dataset

Download Links

Pre‑processing

  • Place the dataset in the ./LEVIR_CC_dataset/ directory.
  • Run python create_input_files.py --min_word_freq 5 for preprocessing.
  • Pre‑processed files can be downloaded from:

Usage Recommendations

  • To ensure fair comparison, future researchers should keep min_word_freq <= 5 or use the provided pre‑processed data (min_word_freq = 5).

Related Publication

  • Title: Remote Sensing Image Change Captioning With Dual‑Branch Transformers: A New Method and a Large Scale Dataset
  • Published in: IEEE Transactions on Geoscience and Remote Sensing (TGRS 2022)
  • Link: IEEE | Lab Server
Need downstream help?

Pair the dataset with AI analysis and content workflows.

Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.

Explore AI studio