SOTAVerified

Zero-Shot Composed Image Retrieval (ZS-CIR)

Given a query composed of a reference image and a relative caption, Composed Image Retrieval (CIR) aims to retrieve target images that are visually similar to the reference one but incorporate the changes specified in the relative caption. The bi-modality of the query provides users with more precise control over the characteristics of the desired image, as some features are more easily described with language, while others can be better expressed visually.

Zero-Shot Composed Image Retrieval (ZS-CIR) is a subtask of CIR that aims to design an approach that manages to combine the reference image and the relative caption without the need for supervised learning.

Papers

Showing 3136 of 36 papers

TitleStatusHype
CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval0
Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy0
Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking0
Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and SimilarityCode0
Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image RetrievalCode0
Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image RetrievalCode0
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.