Microsoft COCO

Microsoft COCO is a dataset that contains images with corresponding annotations for object detection, segmentation, and captioning, and it is used to evaluate the performance of text-to-image retrieval systems.

Papers using Microsoft COCO (4)

TRAP: Targeted Redirecting Of Agentic Preferences2025VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval2025Intra-Modal Constraint Loss For Image-Text Retrieval2022Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task2019