Datasets




Dymanic Facial Expression Recognition dataset (FERV39k)
comprises 4 isolated scenarios, 22 scenes, 7 basic expressions and 26 descriptors.


Industrial Scene Realistic Super-Resolution Dataset (IndSR)
comprises 200 images pixelwise aligned with scale factors of ×2, ×3, and ×4.


Underwater Manually Annotated Background Lights Dataset (MABLs)
comprises 500 significantly valuable underwater images.