Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings

Abstract : Designing powerful tools that support cooking activities has rapidly gained popularity due to the massive amounts of available data, as well as recent advances in machine learning that are capable of analyzing them. In this paper, we propose a cross-modal retrieval model aligning visual and textual data (like pictures of dishes and their recipes) in a shared representation space. We describe an effective learning scheme, capable of tackling large-scale problems, and validate it on the Recipe1M dataset containing nearly 1 million picture-recipe pairs. We show the effectiveness of our approach regarding previous state-of-the-art models and present qualitative results over computational cooking use cases.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01931470
Contributor : David Picard <>
Submitted on : Thursday, November 22, 2018 - 6:28:19 PM
Last modification on : Friday, July 5, 2019 - 3:26:03 PM

Identifiers

Citation

Micael Carvalho, Remi Cadene, David Picard, Laure Soulier, Nicolas Thome, et al.. Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings. The 41st International ACM SIGIR Conference, Jul 2018, Ann Arbor, Michigan, United States. pp.35-44, ⟨10.1145/3209978.3210036⟩. ⟨hal-01931470⟩

Share

Metrics

Record views

174