# Image Captioning on Gibson manually annotated (test)

Source: [Image Captioning on Gibson manually annotated (test)](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test>)

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

Data updated: 2026-03-26T15:39:22.231Z

Evaluation of Image Captioning performance on the test split of the Gibson manually annotated dataset, reporting metrics such as B4, METEOR (M), SPICE (SP), and various CS scores.

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 | Image Captioning |
| Dataset (including any stated split) | Gibson manually annotated (test) |
| Metric | BLEU-4 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [BLEU-4](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=BLEU-4>): Higher is better; unit: SCALAR.

- [METEOR](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=METEOR>): Higher is better; unit: SCALAR.

- [ROUGE-L](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=ROUGE-L>): Higher is better; unit: SCALAR.

- [CI Score](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=CI%20Score>): Higher is better; unit: SCALAR.

- [SPICE](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=SPICE>): Higher is better; unit: SCALAR.

- [CS Score](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=CS%20Score>): Higher is better; unit: SCALAR.

- [Mean CS Score](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=Mean%20CS%20Score>): Higher is better; unit: SCALAR.

- [Median CS Score](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=Median%20CS%20Score>): Higher is better; unit: SCALAR.

- [CS IQR](<https://www.sota2.com/research/sota/image-captioning-on-gibson-manually-annotated-test.md?metric=CS%20IQR>): Lower is better; unit: SCALAR.

## Recorded results

| Method | BLEU-4 | Result date | Report paper |
| --- | --- | --- | --- |
| EPOS-VLM | 19.88 | Not recorded | 69c4bdbd0636e5bf4afc77e5 |
| Galliena et al. | 17.03 | Not recorded | 69c4bdbd0636e5bf4afc77e5 |

### EPOS-VLM

BLEU-4: 19.88. Result ID: 69c5531d47f34ce924afa166.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdbd0636e5bf4afc77e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bdbd0636e5bf4afc77e5.md>)

Recorded evaluation configuration: {"trained\_on":"HM3D"}. This record does not assert independent reproduction.

### Galliena et al.

BLEU-4: 17.03. Result ID: 69c5531d47f34ce924afa165.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdbd0636e5bf4afc77e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b681e209131cea883bf.md>)

Recorded evaluation configuration: {"trained\_on":"HM3D"}. This record does not assert independent reproduction.

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