ICR (Image-Caption Retrieval Dataset)
Introduced by Xie et al. in CCMB: A Large-scale Chinese Cross-modal Benchmark
In this dataset, we collect 200,000 image-text pairs. Each image has a corresponding caption text, which describes the image in detail. It contains two subtasks: image-to-text retrieval and text-to-image retrieval tasks.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
