ESP
Evaluation for Styled Prompt
ImagesTextsIntroduced 2023-06-06
ESP dataset (Evaluation for Styled Prompt dataset) is a benchmark for zero-shot domain-conditional caption generation. ESP is a new dataset focusing on providing multiple styled text targets for the same image. It comprises 4.8k captions from 1k images in the COCO Captions test set. We collect five text domains with everyday usage: blog, social media, instruction, story, and news.
Related Benchmarks
ESPL/Full reference image quality assessment/PLCCESPL/Full reference image quality assessment/SRCCESPL/Image Quality Assessment/PLCCESPL/Image Quality Assessment/SRCCeSports Sensors Dataset/Person Re-Identification/AccuracyeSports Sensors Dataset/Person Re-Identification/LogLosseSports Sensors Dataset/Person Re-Identification/ROC AUCeSports Sensors Dataset/Skills Evaluation/AccuracyeSports Sensors Dataset/Skills Evaluation/LogLosseSports Sensors Dataset/Skills Evaluation/ROC AUC