# Referring Expression Comprehension on RefCOCOg 48 (val-u)

Source: [Referring Expression Comprehension on RefCOCOg 48 (val-u)](<https://www.sota2.com/research/sota/referring-expression-comprehension-on-refcocog-48-val-u>)

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

Data updated: 2026-02-26T05:30:05.454Z

Evaluation of Referring Expression Comprehension performance on the specific '48' subset of the RefCOCOg dataset's val-u split.

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) | RefCOCOg 48 (val-u) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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-refcocog-48-val-u.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SimVG-DB | 87.99 | Not recorded | 68fa756f1e209131cea67e78 |
| SimVG-TB | 87.95 | Not recorded | 68fa756f1e209131cea67e78 |
| SimVG-DB | 86.3 | Not recorded | 68fa756f1e209131cea67e78 |
| SimVG-DB | 85.9 | Not recorded | 68fa756f1e209131cea67e78 |
| OFA-L | 85.89 | Not recorded | 68fa756f1e209131cea67e78 |
| mPLUG-2 | 85.88 | Not recorded | 68fa756f1e209131cea67e78 |
| PolyFormer | 85.83 | Not recorded | 68fa756f1e209131cea67e78 |
| SimVG-TB | 85.38 | Not recorded | 68fa756f1e209131cea67e78 |
| UniTAB | 84.58 | Not recorded | 68fa756f1e209131cea67e78 |
| PolyFormer | 84.46 | Not recorded | 68fa756f1e209131cea67e78 |
| GroundingDINO | 84.15 | Not recorded | 68fa756f1e209131cea67e78 |
| DQ-DETR | 82.76 | Not recorded | 68fa756f1e209131cea67e78 |
| SeqTR | 82.69 | Not recorded | 68fa756f1e209131cea67e78 |
| MDETR | 81.64 | Not recorded | 68fa756f1e209131cea67e78 |
| RefTR | 79.25 | Not recorded | 68fa756f1e209131cea67e78 |
| VILLA\_L | 76.18 | Not recorded | 68fa756f1e209131cea67e78 |
| UNITER\_L | 74.86 | Not recorded | 68fa756f1e209131cea67e78 |

### SimVG-DB

Accuracy: 87.99. Result ID: 6993be213a6c3148491837d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Implementation](<https://github.com/Dmmm1997/SimVG>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-L/32","Pre-train images":"28K"}. This record does not assert independent reproduction.

### SimVG-TB

Accuracy: 87.95. Result ID: 6993be213a6c3148491837d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Implementation](<https://github.com/Dmmm1997/SimVG>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-L/32","Pre-train images":"28K"}. This record does not assert independent reproduction.

### SimVG-DB

Accuracy: 86.3. Result ID: 6993be213a6c3148491837d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Implementation](<https://github.com/Dmmm1997/SimVG>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-B/32","Pre-train images":"174K"}. This record does not assert independent reproduction.

### SimVG-DB

Accuracy: 85.9. Result ID: 6993be213a6c3148491837d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Implementation](<https://github.com/Dmmm1997/SimVG>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-B/32","Pre-train images":"28K"}. This record does not assert independent reproduction.

### OFA-L

Accuracy: 85.89. Result ID: 6993be213a6c3148491837cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea35951.md>)

[Implementation](<https://github.com/OFA-Sys/OFA>)

Recorded evaluation configuration: {"Visual Encoder":"RN152"}. This record does not assert independent reproduction.

### mPLUG-2

Accuracy: 85.88. Result ID: 6993be213a6c3148491837d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f461e209131cea44b05.md>)

[Implementation](<https://github.com/alibaba/AliceMind>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-L/14"}. This record does not assert independent reproduction.

### PolyFormer

Accuracy: 85.83. Result ID: 6993be213a6c3148491837ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428bb.md>)

[Implementation](<https://polyformer.github.io/>)

Recorded evaluation configuration: {"Visual Encoder":"Swin-L"}. This record does not assert independent reproduction.

### SimVG-TB

Accuracy: 85.38. Result ID: 6993be213a6c3148491837d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Implementation](<https://github.com/Dmmm1997/SimVG>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-B/32","Pre-train images":"174K"}. This record does not assert independent reproduction.

### UniTAB

Accuracy: 84.58. Result ID: 6993be213a6c3148491837ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ecb.md>)

Recorded evaluation configuration: {"Visual Encoder":"RN101"}. This record does not assert independent reproduction.

### PolyFormer

Accuracy: 84.46. Result ID: 6993be213a6c3148491837cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428bb.md>)

[Implementation](<https://polyformer.github.io/>)

Recorded evaluation configuration: {"Visual Encoder":"Swin-B"}. This record does not assert independent reproduction.

### GroundingDINO

Accuracy: 84.15. Result ID: 6993be213a6c3148491837cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6055d.md>)

[Implementation](<https://github.com/IDEA-Research/GroundingDINO>)

Recorded evaluation configuration: {"Visual Encoder":"Swin-T"}. This record does not assert independent reproduction.

### DQ-DETR

Accuracy: 82.76. Result ID: 6993be213a6c3148491837cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e1f1e209131cea3df1e.md>)

Recorded evaluation configuration: {"Visual Encoder":"RN101"}. This record does not assert independent reproduction.

### SeqTR

Accuracy: 82.69. Result ID: 6993be213a6c3148491837c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e0c1e209131cea3dad7.md>)

[Implementation](<https://github.com/sean-zhuh/SeqTR>)

Recorded evaluation configuration: {"Visual Encoder":"DN53"}. This record does not assert independent reproduction.

### MDETR

Accuracy: 81.64. Result ID: 6993be213a6c3148491837c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af51e209131cea2b5a9.md>)

[Implementation](<https://github.com/ashkamath/mdetr>)

Recorded evaluation configuration: {"Visual Encoder":"RN101"}. This record does not assert independent reproduction.

### RefTR

Accuracy: 79.25. Result ID: 6993be213a6c3148491837c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27dec.md>)

Recorded evaluation configuration: {"Visual Encoder":"RN101"}. This record does not assert independent reproduction.

### VILLA\_L

Accuracy: 76.18. Result ID: 6993be213a6c3148491837c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d368.md>)

[Implementation](<https://github.com/zhegan27/VILLA>)

Recorded evaluation configuration: {"Visual Encoder":"RN101"}. This record does not assert independent reproduction.

### UNITER\_L

Accuracy: 74.86. Result ID: 6993be213a6c3148491837c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e78.md>)

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

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

Recorded evaluation configuration: {"Visual Encoder":"RN101"}. This record does not assert independent reproduction.

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