Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model

About

Nowadays, driven by the increasing concern on diet and health, food computing has attracted enormous attention from both industry and research community. One of the most popular research topics in this domain is Food Retrieval, due to its profound influence on health-oriented applications. In this paper, we focus on the task of cross-modal retrieval between food images and cooking recipes. We present Modality-Consistent Embedding Network (MCEN) that learns modality-invariant representations by projecting images and texts to the same embedding space. To capture the latent alignments between modalities, we incorporate stochastic latent variables to explicitly exploit the interactions between textual and visual features. Importantly, our method learns the cross-modal alignments during training but computes embeddings of different modalities independently at inference time for the sake of efficiency. Extensive experimental results clearly demonstrate that the proposed MCEN outperforms all existing approaches on the benchmark Recipe1M dataset and requires less computational cost.

Han Fu, Rui Wu, Chenghao Liu, Jianling Sun• 2020

Related benchmarks

TaskDatasetResultRank
Image-to-recipe retrievalRecipe1M 10k setup (test)
Recall@120.3
125
Recipe-to-image retrievalRecipe1M 10k setup (test)
R@121.4
120
Image-to-recipe retrievalRecipe1M 1k setup (test)
Recall@148.2
116
Recipe-to-image retrievalRecipe1M 1k setup (test)
Recall@148.4
110
Image-to-recipe retrievalRecipe1M 1.0 (test)
Median Rank2
35
Recipe-to-image retrievalRecipe1M 1.0 (test)
MedR1.9
30
Cross-modal Retrieval (Image-to-Recipe)Recipe1M v1 (1k)
MedR2
28
Cross-modal Retrieval (Recipe-to-Image)Recipe1M 10k v1
Median Rank6.6
13
Cross-modal Retrieval (Recipe-to-Image)Recipe1M v1 (1k)
Median Rank1.9
13
Showing 9 of 9 rows

Other info

Follow for update