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/Referring Expression Segmentation

Referring Expression Segmentation

74 benchmarks145 papers

The task aims at labeling the pixels of an image or video that represent an object instance referred by a linguistic expression. In particular, the referring expression (RE) must allow the identification of an individual object in a discourse or scene (the referent). REs unambiguously identify the target instance.

Benchmarks

Referring Expression Segmentation on RefCoCo val

Overall IoUMean IoUmIoUPrecision@0.5Precision@0.6Precision@0.7Precision@0.8Precision@0.9

Referring Expression Segmentation on RefCOCO+ val

Overall IoUMean IoU

Referring Expression Segmentation on Refer-YouTube-VOS (2021 public validation)

J&FJF

Referring Expression Segmentation on RefCOCO+ testA

Overall IoUMean IoUmIoU

Referring Expression Segmentation on RefCOCO+ test B

Overall IoUMean IoUmIoU

Referring Expression Segmentation on A2D Sentences

IoU overallIoU meanPrecision@0.5Precision@0.9Precision@0.6Precision@0.7Precision@0.8AP

Referring Expression Segmentation on J-HMDB

Precision@0.5Precision@0.6Precision@0.7Precision@0.8Precision@0.9IoU overallIoU meanAP

Referring Expression Segmentation on RefCOCOg-val

Overall IoUMean IoUIoUmIoU

Referring Expression Segmentation on DAVIS 2017 (val)

J&F 1st frameJ&F Full videoJ&F scoreZero-Shot Transfer

Referring Expression Segmentation on RefCOCOg-test

Overall IoUMean IoUmIoU

Referring Expression Segmentation on gRefCOCO

gIoUcIoU

Referring Expression Segmentation on RefCOCO testA

Overall IoUMean IoUmIoU

Referring Expression Segmentation on RefCOCO testB

Overall IoUMean IoUmIoU

Referring Expression Segmentation on PhraseCut

Mean IoUPr@0.5Pr@0.7Pr@0.9

Referring Expression Segmentation on RefCOCO

IoUIoU (%)

Referring Expression Segmentation on ReferIt

Overall IoUMean IoU

Referring Expression Segmentation on Refer-YouTube-VOS

Mean IoUPrecision@0.5Precision@0.9

Referring Expression Segmentation on A2Dre test

Overall IoUMean IoU

Referring Expression Segmentation on CLEVR-Ref+

IoU

Referring Expression Segmentation on G-Ref test A

Overall IoU

Referring Expression Segmentation on G-Ref test B

Overall IoU

Referring Expression Segmentation on G-Ref val

Overall IoU

Referring Expression Segmentation on Referring Expressions for DAVIS 2016 & 2017

FJJ&F 1st frame