TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Composed Image Retrieval (CoIR)

Composed Image Retrieval (CoIR)

23 benchmarks14 papers

Composed Image Retrieval (CoIR) is the task involves retrieving images from a large database based on a query composed of multiple elements, such as text, images, and sketches. The goal is to develop algorithms that can understand and combine multiple sources of information to accurately retrieve images that match the query, extending the user’s expression ability.

Benchmarks

Composed Image Retrieval (CoIR) on CIRR

R@5R@1R@10R@50Rsubset@1

Composed Image Retrieval (CoIR) on CIRCO

mAP@10MAP@5mAP@50mAP@25

Composed Image Retrieval (CoIR) on Fashion IQ

(Recall@10+Recall@50)/2R@10R@50

Composed Image Retrieval (CoIR) on ImageNet-R

(Recall@10+Recall@50)/2mAP

Composed Image Retrieval (CoIR) on ImageNet

Average Recall

Composed Image Retrieval (CoIR) on COCO (Common Objects in Context)

Actions Recall@5

Composed Image Retrieval (CoIR) on GeneCIS

A-R@1A-R@1

Composed Image Retrieval (CoIR) on Large Time Lags Location (LTLL)

mAP

Composed Image Retrieval (CoIR) on MiniDomainNet

mAP

Composed Image Retrieval (CoIR) on NICO++

mAP

Composed Image Retrieval (CoIR) on PatternCom

mAP

Composed Image Retrieval (CoIR) on FashionIQ

R@10