Recipe-1M
Emerging4papers using it
2021first seen
The 'Recipe-1M' dataset contains one million food images paired with their corresponding recipe texts and is used to evaluate cross-modal retrieval methods between food images and recipe texts.
Papers using Recipe-1M (4)
- SIMMER: Cross-Modal Food Image--Recipe Retrieval via MLLM-Based EmbeddingLearning Structural Representations for Recipe Generation and Food
RetrievalRoDE: Linear Rectified Mixture of Diverse Experts for Food Large
Multi-Modal ModelsLearning Joint Embedding with Modality Alignments for Cross-Modal
Retrieval of Recipes and Food Images