TESMR progressively enhances multimodal recipe features through content-based, relation-based, and learning-based stages, achieving 7-15% higher Recall@10 than baselines on two real-world datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Raw Features to Effective Embeddings: A Three-Stage Approach for Multimodal Recipe Recommendation
TESMR progressively enhances multimodal recipe features through content-based, relation-based, and learning-based stages, achieving 7-15% higher Recall@10 than baselines on two real-world datasets.