Y-J-Ju/MIRe_ViD2R download history

Y-J-Ju/MIRe_ViD2R is a text retrieval dataset on the Hugging Face Hub. In the last 30 days it was downloaded 28 times (4 in the last 7 days), and 1,014 times in total. It ranks #289,218 among datasets by monthly downloads.

MIRe Pre-training Dataset for Multimodal Query Retrieval This repository contains the pre-training dataset used in our work on MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval. The dataset is designed for training multimodal r

Models trained on MIRe_ViD2R

1 models list it as training data.

Open Y-J-Ju/MIRe_ViD2R on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.