# Egocentric Interaction Analysis on Ego-IRGBench (test)

Source: [Egocentric Interaction Analysis on Ego-IRGBench (test)](<https://www.sota2.com/research/sota/egocentric-interaction-analysis-on-ego-irgbench-test>)

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

Data updated: 2026-05-15T09:13:01.211Z

Evaluation of model performance on the test split of the Ego-IRGBench dataset for the task of Egocentric Interaction Analysis, measured using generation-based metrics like 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 | Egocentric Interaction Analysis |
| Dataset (including any stated split) | Ego-IRGBench (test) |
| Metric | METEOR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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/egocentric-interaction-analysis-on-ego-irgbench-test.md?metric=METEOR>): Higher is better; unit: SCALAR.

- [CIDEr](<https://www.sota2.com/research/sota/egocentric-interaction-analysis-on-ego-irgbench-test.md?metric=CIDEr>): Higher is better; unit: SCALAR.

## Recorded results

| Method | METEOR | Result date | Report paper |
| --- | --- | --- | --- |
| ANNEXE | 0.563 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| EARL | 0.542 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| ANNEXE\* | 0.536 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Seg-Zero | 0.309 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Seg-R1-7B | 0.292 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Seg-R1-3B | 0.268 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Sa2VA-InternVL3-8B | 0.207 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Qwen2.5VL-7B | 0.206 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Sa2VA-8B | 0.188 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| EgoThinker | 0.182 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| InternVL2.5-7B | 0.177 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| UniPixel-7B | 0.165 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Qwen2.5-VL-3B | 0.158 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Qwen3-VL-8B | 0.136 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |
| Qwen3-VL-4B | 0.134 | Not recorded | 6a06a8b6dbc836b87d82a1d9 |

### ANNEXE

METEOR: 0.563. Result ID: 6a06e38d47f34ce924eec703.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c61e209131cea75436.md>)

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

Recorded evaluation configuration: {"Type":"Ego"}. This record does not assert independent reproduction.

### EARL

METEOR: 0.542. Result ID: 6a06e38d47f34ce924eec70a.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

Recorded evaluation configuration: {"Type":"Ego"}. This record does not assert independent reproduction.

### ANNEXE\*

METEOR: 0.536. Result ID: 6a06e38d47f34ce924eec702.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c61e209131cea75436.md>)

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

Recorded evaluation configuration: {"Type":"Ego"}. This record does not assert independent reproduction.

### Seg-Zero

METEOR: 0.309. Result ID: 6a06e38d47f34ce924eec709.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79b81e209131cea7f19c.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Seg-R1-7B

METEOR: 0.292. Result ID: 6a06e38d47f34ce924eec708.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ae1e209131cea7ed93.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Seg-R1-3B

METEOR: 0.268. Result ID: 6a06e38d47f34ce924eec707.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ae1e209131cea7ed93.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Sa2VA-InternVL3-8B

METEOR: 0.207. Result ID: 6a06e38d47f34ce924eec704.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ec1e209131cea6ff2c.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Qwen2.5VL-7B

METEOR: 0.206. Result ID: 6a06e38d47f34ce924eec6ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Sa2VA-8B

METEOR: 0.188. Result ID: 6a06e38d47f34ce924eec705.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ec1e209131cea6ff2c.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### EgoThinker

METEOR: 0.182. Result ID: 6a06e38d47f34ce924eec701.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2ebd.md>)

Recorded evaluation configuration: {"Type":"Ego"}. This record does not assert independent reproduction.

### InternVL2.5-7B

METEOR: 0.177. Result ID: 6a06e38d47f34ce924eec700.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### UniPixel-7B

METEOR: 0.165. Result ID: 6a06e38d47f34ce924eec706.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c691e209131cea8deed.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B

METEOR: 0.158. Result ID: 6a06e38d47f34ce924eec6fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

METEOR: 0.136. Result ID: 6a06e38d47f34ce924eec6fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

### Qwen3-VL-4B

METEOR: 0.134. Result ID: 6a06e38d47f34ce924eec6fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a8b6dbc836b87d82a1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Type":"Gen"}. This record does not assert independent reproduction.

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