# Referring Expression Comprehension on RefCOCO+ (test)

Source: [Referring Expression Comprehension on RefCOCO+ (test)](<https://www.sota2.com/research/sota/referring-expression-comprehension-on-refcoco-plus-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:31:26.004Z

Evaluation of Referring Expression Comprehension performance on the general test split of the RefCOCO+ dataset, typically measured using Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Referring Expression Comprehension |
| Dataset (including any stated split) | RefCOCO+ (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/referring-expression-comprehension-on-refcoco-plus-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AP](<https://www.sota2.com/research/sota/referring-expression-comprehension-on-refcoco-plus-test.md?metric=AP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Our SAT-\>ST | 74.22 | Not recorded | 68fa676c1e209131cea1603c |
| UNITER \[8\] | 73.73 | Not recorded | 68fa676c1e209131cea1603c |
| Our SAT | 73.25 | Not recorded | 68fa676c1e209131cea1603c |
| UNITER \[8\] | 72.9 | Not recorded | 68fa676c1e209131cea1603c |

### Our SAT-\>ST

Accuracy: 74.22. Result ID: 698d332b8b517eb4331fbc5c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Implementation](<https://github.com/facebookresearch/vilbert-multi-task>)

Recorded evaluation configuration: {"Backbone":"BERTB","Training Strategy":"All-Task Pretraining + Single-Task Finetuning","Number of Parameters":"3B","Number of Models":"12 x 250M"}. This record does not assert independent reproduction.

### UNITER \[8\]

Accuracy: 73.73. Result ID: 698d332b8b517eb4331fbc5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f91e209131cea1989f.md>)

[Implementation](<https://github.com/ChenRocks/UNITER>)

Recorded evaluation configuration: {"Backbone":"BERTL","Number of Parameters":"2.1B","Number of Models":"7 x 303M"}. This record does not assert independent reproduction.

### Our SAT

Accuracy: 73.25. Result ID: 698d332b8b517eb4331fbc5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Implementation](<https://github.com/facebookresearch/vilbert-multi-task>)

Recorded evaluation configuration: {"Backbone":"BERTB","Training Strategy":"All-Task (AT)","Number of Parameters":"270M","Number of Models":"1 x 270M"}. This record does not assert independent reproduction.

### UNITER \[8\]

Accuracy: 72.9. Result ID: 698d332b8b517eb4331fbc59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f91e209131cea1989f.md>)

[Implementation](<https://github.com/ChenRocks/UNITER>)

Recorded evaluation configuration: {"Backbone":"BERTB","Number of Parameters":"602M","Number of Models":"7 x 86M"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.