AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features

CVPR 2022 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 161 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Combine CLIP image and text features with a learned Combiner networkFashionIQ retrieval · FashionIQ validation (average)R@10: 29.08 -> 35.39Helped
Combine CLIP image and text features with a learned Combiner networkFashionIQ retrieval · FashionIQ validation (average)R@50: 54.70 -> 59.03Helped
Combine CLIP image and text features with a learned Combiner networkCIRR retrieval · CIRR testR@1: 19.55 -> 33.59Helped
Combine CLIP image and text features with a learned Combiner networkCIRR retrieval · CIRR testR@5: 52.55 -> 65.35Helped
Combine CLIP image and text features with a learned Combiner networkCIRR retrieval · CIRR testR@10: 68.39 -> 77.35Helped
Combine CLIP image and text features with a learned Combiner networkCIRR retrieval · CIRR testR@50: 92.38 -> 95.21Helped
Combine CLIP image and text features with a learned Combiner networkCIRR retrieval · CIRR testRSubset@1: 39.20 -> 62.39Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy