paper-with-me

Composed Image Retrieval (CoIR)

2개 벤치마크 · 논문 14편 · 이 태스크의 논문 보기 →

Benchmarks

CIRR

결과 2개

Fashion IQ

결과 2개

Most implemented

Papers

Composed Image Retrieval for Remote Sensing

2024-05-24 · Bill Psomas, Ioannis Kakogeorgiou, Nikos Efthymiadis, Giorgos Tolias 외

This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descriptive power over unimodal queries, eith…

Composed Image Retrieval (CoIR)DescriptiveImage RetrievalLanguage Modeling+3

iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval

2024-05-05 · Lorenzo Agnolucci, Alberto Baldrati, Marco Bertini, Alberto del Bimbo

Given a query consisting of a reference image and a relative caption, Composed Image Retrieval (CIR) aims to retrieve target images visually similar to the reference one while incorporating the changes specified in the r…

BenchmarkingComposed Image Retrieval (CoIR)Image RetrievalRetrieval+1

Sentence-level Prompts Benefit Composed Image Retrieval

2023-10-09 · Yang Bai, Xinxing Xu, Yong liu, Salman Khan 외

Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adopt the late-fusion strategy to combine vi…

AttributeComposed Image Retrieval (CoIR)Image RetrievalRetrieval+1

CoVR-2: Automatic Data Construction for Composed Video Retrieval

2023-08-28 · Lucas Ventura, Antoine Yang, Cordelia Schmid, Gül Varol

Composed Image Retrieval (CoIR) has recently gained popularity as a task that considers both text and image queries together, to search for relevant images in a database. Most CoIR approaches require manually annotated d…

Composed Image Retrieval (CoIR)Composed Video Retrieval (CoVR)Image RetrievalLanguage Modelling+5

Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder

2023-05-25 · Zheyuan Liu, Weixuan Sun, Damien Teney, Stephen Gould

Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus…

Composed Image Retrieval (CoIR)Image RetrievalRerankingRe-Ranking+2

Bi-directional Training for Composed Image Retrieval via Text Prompt Learning

2023-03-29 · Zheyuan Liu, Weixuan Sun, Yicong Hong, Damien Teney 외

Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes. Existing approaches to solving this challenging …

Composed Image Retrieval (CoIR)Image RetrievalPrompt LearningRetrieval

전체 14편 보기 →