# Visual Grounding on RefCOCOg umd (test)

Source: [Visual Grounding on RefCOCOg umd (test)](<https://www.sota2.com/research/sota/visual-grounding-on-refcocog-umd-test>)

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

Data updated: 2026-02-26T05:54:45.274Z

Evaluation of Visual Grounding performance on the test split of the RefCOCOg UMD dataset, measured using P@1 and oIoU.

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 | Visual Grounding |
| Dataset (including any stated split) | RefCOCOg umd (test) |
| Metric | P@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [P@1](<https://www.sota2.com/research/sota/visual-grounding-on-refcocog-umd-test.md?metric=P%401>): Higher is better; unit: PERCENT.

- [oIoU](<https://www.sota2.com/research/sota/visual-grounding-on-refcocog-umd-test.md?metric=oIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | P@1 | Result date | Report paper |
| --- | --- | --- | --- |
| APE (D) | 80.1 | Not recorded | 68fa71581e209131cea50b01 |
| APE (B) | 79.9 | Not recorded | 68fa71581e209131cea50b01 |
| APE (C) | 79.5 | Not recorded | 68fa71581e209131cea50b01 |
| Grounding DINO | 72 | Not recorded | 68fa71581e209131cea50b01 |
| GLIP | 66.8 | Not recorded | 68fa71581e209131cea50b01 |
| KOSMOS-2 | 61.6 | Not recorded | 68fa71581e209131cea50b01 |
| APE (A) | 40.5 | Not recorded | 68fa71581e209131cea50b01 |

### APE (D)

P@1: 80.1. Result ID: 6991ab083a6c31484909c713.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Implementation](<https://github.com/shenyunhang/APE>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### APE (B)

P@1: 79.9. Result ID: 6991ab083a6c31484909c711.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Implementation](<https://github.com/shenyunhang/APE>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### APE (C)

P@1: 79.5. Result ID: 6991ab083a6c31484909c712.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Implementation](<https://github.com/shenyunhang/APE>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### Grounding DINO

P@1: 72. Result ID: 6991ab083a6c31484909c70e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

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

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

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

### GLIP

P@1: 66.8. Result ID: 6991ab083a6c31484909c70d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd91e209131cea36418.md>)

[Implementation](<https://github.com/microsoft/GLIP>)

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

### KOSMOS-2

P@1: 61.6. Result ID: 6991ab083a6c31484909c70f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa700a1e209131cea48c7f.md>)

[Implementation](<https://aka.ms/kosmos-2>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### APE (A)

P@1: 40.5. Result ID: 6991ab083a6c31484909c710.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71581e209131cea50b01.md>)

[Implementation](<https://github.com/shenyunhang/APE>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

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