Loom combines slot-constrained embedding retrieval with multi-objective scoring and two new CLIP-based techniques to generate coherent outfits, achieving 3.3x higher scores and 42% fewer violations than random baselines on a 620-item catalog.
OutfitTransformer: Learning outfit representations for fashion recommendation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Loom: Hybrid Retrieval-Scoring Outfit Recommendation with Semantic Material Compatibility and Occasion-Aware Embedding Priors
Loom combines slot-constrained embedding retrieval with multi-objective scoring and two new CLIP-based techniques to generate coherent outfits, achieving 3.3x higher scores and 42% fewer violations than random baselines on a 620-item catalog.