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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 36 papers

TitleStatusHype
Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval—0
MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval—0
CoLLM: A Large Language Model for Composed Image RetrievalCode1
Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image RetrievalCode1
ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective ReasoningCode1
Data-Efficient Generalization for Zero-shot Composed Image Retrieval—0
CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval—0
PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrieval—0
SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval—0
MegaPairs: Massive Data Synthesis For Universal Multimodal RetrievalCode3
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.