Multi-30K

The Multi-30K dataset contains image-caption pairs in multiple languages and is used to evaluate multimodal machine translation performance.

Papers using Multi-30K (13)

Dual-branch Prompting for Multimodal Machine Translation2025Towervision: Understanding And Improving Multilinguality In Vision-language Models2025GIIFT: Graph-guided Inductive Image-free Multimodal Machine Translation2025Image search using multilingual texts: a cross-modal learning approach between image and text2019 · 10 citesLightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval2021 · 6 citesMultilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models2021 · 5 citesMulti-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations2019 · 1 citesVisual Agreement Regularized Training for Multi-Modal Machine Translation2019 · 1 citesMake Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation2024 · 1 citesMuMUR : Multilingual Multimodal Universal Retrieval2022CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer2023Probing the Need for Visual Context in Multimodal Machine Translation2019Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task2019