# Region Captioning on RefDrone (val)

Source: [Region Captioning on RefDrone (val)](<https://www.sota2.com/research/sota/region-captioning-on-refdrone-val>)

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

Data updated: 2026-04-28T09:35:20.484Z

Evaluation of Region Captioning performance on the validation split of the RefDrone dataset, measured using METEOR and CIDEr.

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 | Region Captioning |
| Dataset (including any stated split) | RefDrone (val) |
| Metric | METEOR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [METEOR](<https://www.sota2.com/research/sota/region-captioning-on-refdrone-val.md?metric=METEOR>): Higher is better; unit: PERCENT.

- [CIDEr](<https://www.sota2.com/research/sota/region-captioning-on-refdrone-val.md?metric=CIDEr>): Higher is better; unit: SCALAR.

## Recorded results

| Method | METEOR | Result date | Report paper |
| --- | --- | --- | --- |
| ChatRex-7B + Proposed method | 26 | Not recorded | 69f03f2f55a3c32af89fa1cf |
| ChatRex-7B + Naive finetuning | 25.3 | Not recorded | 69f03f2f55a3c32af89fa1cf |
| Groma-7B | 12.3 | Not recorded | 69f03f2f55a3c32af89fa1cf |
| ChatRex-7B | 7.5 | Not recorded | 69f03f2f55a3c32af89fa1cf |

### ChatRex-7B + Proposed method

METEOR: 26. Result ID: 69f07f4447f34ce924d6c729.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2f55a3c32af89fa1cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f2f55a3c32af89fa1cf.md>)

Recorded evaluation configuration: {"framework":"Language-Guided Semantic Cues (LGSCs)"}. This record does not assert independent reproduction.

### ChatRex-7B + Naive finetuning

METEOR: 25.3. Result ID: 69f07f4447f34ce924d6c728.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2f55a3c32af89fa1cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77581e209131cea72912.md>)

Recorded evaluation configuration: {"adaptation":"Naive finetuning"}. This record does not assert independent reproduction.

### Groma-7B

METEOR: 12.3. Result ID: 69f07f4447f34ce924d6c726.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2f55a3c32af89fa1cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ee1e209131cea595bc.md>)

[Implementation](<https://groma-mllm.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ChatRex-7B

METEOR: 7.5. Result ID: 69f07f4447f34ce924d6c727.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2f55a3c32af89fa1cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77581e209131cea72912.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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