# Video Summarization on Ego4D v1 (test)

Source: [Video Summarization on Ego4D v1 (test)](<https://www.sota2.com/research/sota/video-summarization-on-ego4d-v1-test>)

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

Data updated: 2026-06-02T08:46:04.846Z

Evaluation of Video Summarization performance on the test split of the Ego4D v1 dataset, measured using metrics like CIDEr, METEOR, and ROUGE\_L.

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 | Video Summarization |
| Dataset (including any stated split) | Ego4D v1 (test) |
| Metric | CIDEr |
| Unit | SCALAR |
| 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

- [CIDEr](<https://www.sota2.com/research/sota/video-summarization-on-ego4d-v1-test.md?metric=CIDEr>): Higher is better; unit: SCALAR.

- [METEOR](<https://www.sota2.com/research/sota/video-summarization-on-ego4d-v1-test.md?metric=METEOR>): Higher is better; unit: SCALAR.

- [ROUGE\_L](<https://www.sota2.com/research/sota/video-summarization-on-ego4d-v1-test.md?metric=ROUGE_L>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CIDEr | Result date | Report paper |
| --- | --- | --- | --- |
| Video ReCap | 46.88 | Not recorded | 6a1e63c5dbd7150506f853b6 |
| LaViLa + FLANT5 | 39.13 | Not recorded | 6a1e63c5dbd7150506f853b6 |
| LaViLa + GPT2 | 38.22 | Not recorded | 6a1e63c5dbd7150506f853b6 |
| LaViLa | 24.63 | Not recorded | 6a1e63c5dbd7150506f853b6 |
| FLOWNAR + Llama3 | 11.2 | Not recorded | 6a1e63c5dbd7150506f853b6 |
| LaViLa + GPT3.5 | 5.79 | Not recorded | 6a1e63c5dbd7150506f853b6 |
| BLIP2 + GPT3.5 | 5.68 | Not recorded | 6a1e63c5dbd7150506f853b6 |

### Video ReCap

CIDEr: 46.88. Result ID: 6a1e9745fbc373592c18cd40.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73311e209131cea5b079.md>)

[Implementation](<https://sites.google.com/view/vidrecap>)

Recorded evaluation configuration: {"Finetuned":"true"}. This record does not assert independent reproduction.

### LaViLa + FLANT5

CIDEr: 39.13. Result ID: 6a1e9745fbc373592c18cd3e.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e533.md>)

Recorded evaluation configuration: {"Finetuned":"true"}. This record does not assert independent reproduction.

### LaViLa + GPT2

CIDEr: 38.22. Result ID: 6a1e9745fbc373592c18cd3d.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e533.md>)

Recorded evaluation configuration: {"Finetuned":"true"}. This record does not assert independent reproduction.

### LaViLa

CIDEr: 24.63. Result ID: 6a1e9745fbc373592c18cd3f.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e533.md>)

Recorded evaluation configuration: {"Finetuned":"true"}. This record does not assert independent reproduction.

### FLOWNAR + Llama3

CIDEr: 11.2. Result ID: 6a1e9745fbc373592c18cd43.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

Recorded evaluation configuration: {"Finetuned":"false"}. This record does not assert independent reproduction.

### LaViLa + GPT3.5

CIDEr: 5.79. Result ID: 6a1e9745fbc373592c18cd42.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e533.md>)

Recorded evaluation configuration: {"Finetuned":"false"}. This record does not assert independent reproduction.

### BLIP2 + GPT3.5

CIDEr: 5.68. Result ID: 6a1e9745fbc373592c18cd41.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c5dbd7150506f853b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"Finetuned":"false"}. This record does not assert independent reproduction.

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