[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
-
Updated
Sep 5, 2023 - Python
#
fashioniq
Here are 2 public repositories matching this topic...
We systematically compare three VLM-based composed image retrieval approaches for fashion e-commerce - embedding fusion, VLM reranking, and textual inversion, across local and frontier models (Qwen-3B, Gemini 2.5 Flash, GPT-4o) on the Fashion-IQ benchmark, analyzing accuracy-latency tradeoffs.
-
Updated
Apr 15, 2026 - Python
Improve this page
Add a description, image, and links to the fashioniq topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the fashioniq topic, visit your repo's landing page and select "manage topics."