mlsanityData to 7 Oct 2026

"Does it come in black?" CLIP-like models are zero-shot recommenders

arXiv 2204.02473 ↗First posted 5 Apr 2022cs.IR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Product discovery is a crucial component for online shopping. However, item-to-item recommendations today do not allow users to explore changes along selected dimensions: given a query item, can a model suggest something similar but in a different color? We consider item recommendations of the comparative nature (e.g. "something darker") and show how CLIP-based models can support this use case in a zero-shot manner. Leveraging a large model built for fashion, we introduce GradREC and its industry potential, and offer a first rounded assessment of its strength and weaknesses.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 38 references that are in the map. First posted on arXiv 5 Apr 2022.

Builds on

19 of 38 references.

References · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  3. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  4. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
  5. 2019On the "steerability" of generative adversarial networkscited by 247
  6. 2020A Survey on Conversational Recommender Systemscited by 142
  7. 2017ExprGAN: Facial Expression Editing with Controllable Expression Intensitycited by 47
  8. 2019Product Knowledge Graph Embedding for E-commercecited by 36
  9. 2020Try This Instead: Personalized and Interpretable Substitute Recommendationcited by 34
  10. 2021Generate Natural Language Explanations for Recommendationcited by 22
  11. 2020Fantastic Embeddings and How to Align Them: Zero-Shot Inference in a Multi-Shop Scenariocited by 16
  12. 2021SIGIR 2021 E-Commerce Workshop Data Challengecited by 11
7 more
  1. 2021Query2Prod2Vec Grounded Word Embeddings for eCommercecited by 8
  2. 2020BERT Goes Shopping: Comparing Distributional Models for Product Representationscited by 7
  3. 2021Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interactioncited by 5
  4. 2018A Multimodal Recommender System for Large-scale Assortment Generation in E-commercecited by 4
  5. 2021Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representationscited by 4
  6. 2021"Are you sure?": Preliminary Insights from Scaling Product Comparisons to Multiple Shopscited by 4
  7. 2019On the Importance of News Content Representation in Hybrid Neural Session-based Recommender Systemscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2022Contrastive language and vision learning of general fashion conceptscited by 41
  2. 2023Reasonable Scale Machine Learning with Open-Source Metaflowcited by 5
  3. 2023(Vector) Space is Not the Final Frontier: Product Search as Program Synthesiscited by 0
  4. 2024ENCLIP: Ensembling and Clustering-Based Contrastive Language-Image Pretraining for Fashion Multimodal Search with Limited Data and Low-Quality Imagescited by 0