COCO Captions

The 'COCO Captions' dataset contains images paired with descriptive captions and is used to evaluate the performance of models in generating and understanding image descriptions.

Papers using COCO Captions (3)

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning2026Beyond Generation: Multi-Hop Reasoning for Factual Accuracy in Vision-Language Models2025MMBench: Is Your Multi-modal Model an All-around Player?2023 · 33 cites