# Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning

arXiv: https://arxiv.org/abs/2012.01345 · HTML: https://mlsanity.com/paper/2012.01345/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities](https://mlsanity.com/paper/2210.15359/) (2022)
- [Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations](https://mlsanity.com/paper/2306.02092/) (2023)
- [Modality-Invariant Bidirectional Temporal Representation Distillation Network for Missing Multimodal Sentiment Analysis](https://mlsanity.com/paper/2501.05474/) (2025)
- [Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval](https://mlsanity.com/paper/2204.09730/) (2022)
- [Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval](https://mlsanity.com/paper/2212.04267/) (2022)
- [MALM: Mask Augmentation based Local Matching for Food-Recipe Retrieval](https://mlsanity.com/paper/2305.11327/) (2023)
- [Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval](https://mlsanity.com/paper/2510.20393/) (2025)
- [Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval](https://mlsanity.com/paper/2511.15201/) (2025)
- [SIMMER: Cross-Modal Food Image--Recipe Retrieval via MLLM-Based Embedding](https://mlsanity.com/paper/2604.15628/) (2026)

## Abstract (arXiv)

Computational food analysis (CFA) naturally requires multi-modal evidence of a particular food, e.g., images, recipe text, etc. A key to making CFA possible is multi-modal shared representation learning, which aims to create a joint representation of the multiple views (text and image) of the data. In this work we propose a method for food domain cross-modal shared representation learning that preserves the vast semantic richness present in the food data. Our proposed method employs an effective transformer-based multilingual recipe encoder coupled with a traditional image embedding architecture. Here, we propose the use of imperfect multilingual translations to effectively regularize the model while at the same time adding functionality across multiple languages and alphabets. Experimental analysis on the public Recipe1M dataset shows that the representation learned via the proposed method significantly outperforms the current state-of-the-arts (SOTA) on retrieval tasks. Furthermore, the representational power of the learned representation is demonstrated through a generative food image synthesis model conditioned on recipe embeddings. Synthesized images can effectively reproduce the visual appearance of paired samples, indicating that the learned representation captures the joint semantics of both the textual recipe and its visual content, thus narrowing the modality gap.