atlas

Research map / Vision-language and multimodal / Cross-modal learning

ST-Bridge: Bridging Sketch and Text with Large Language Models for Coarse-to-Fine Image Retrieval

NeurIPS 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes ST-Bridge, a coarse-to-fine sketch-text image retrieval method that uses large language models to bridge sketch and text modalities.

Problem

Sketch-text image retrieval, which must combine free-hand sketches and text descriptions to find natural images; difficult due to large representational gaps between modalities and matching fine details in complex scenes.

Approach

Uses large language models to bridge sketch and text representations in a coarse-to-fine retrieval pipeline, in contrast to prior simple feature fusion or global alignment approaches.

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