{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cross-modal-food-retrieval-learning-a-joint","title":"Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism","arxiv_id":"2003.03955","date":"2020-03-09","proceeding":null,"authors":["Hao Wang","Doyen Sahoo","Chenghao Liu","Ke Shu","Palakorn Achananuparp","Ee-Peng Lim","Steven C. H. Hoi"],"abstract":"Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc. In this paper, we investigate cross-modal retrieval between food images and cooking recipes. The goal is to learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. Two major challenges in addressing this problem are 1) large intra-variance and small inter-variance across cross-modal food data; and 2) difficulties in obtaining discriminative recipe representations. To address these two problems, we propose Semantic-Consistent and Attention-based Networks (SCAN), which regularize the embeddings of the two modalities through aligning output semantic probabilities. Besides, we exploit a self-attention mechanism to improve the embedding of recipes. We evaluate the performance of the proposed method on the large-scale Recipe1M dataset, and show that we can outperform several state-of-the-art cross-modal retrieval strategies for food images and cooking recipes by a significant margin.","url_abs":"https://arxiv.org/abs/2003.03955v3","url_pdf":"https://arxiv.org/pdf/2003.03955v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-recipe1m","task":"Cross-Modal Retrieval","dataset":"Recipe1M","model":"SCAN","rank_in_archive_order":7,"of":9,"metrics":{"Image-to-text R@1":"54.0","Text-to-image R@1":"54.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.03955","atlas_url":"https://app.syntology.ai/?focus=2003.03955","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}