# Video Detail Captioning on VDC

Source: [Video Detail Captioning on VDC](<https://www.sota2.com/research/sota/video-detail-captioning-on-vdc>)

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

Data updated: 2026-03-24T13:45:48.207Z

Evaluation of Video Detail Captioning performance on the VDC dataset, measured using component-wise metrics including Camera, Short, Background, Main Object, Detail, and an overall Score.

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 Detail Captioning |
| Dataset (including any stated split) | VDC |
| Metric | Camera Component Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 28 of 28 |
| 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

- [Camera Component Score](<https://www.sota2.com/research/sota/video-detail-captioning-on-vdc.md?metric=Camera%20Component%20Score>): Higher is better; unit: SCALAR.

- [Short Component Score](<https://www.sota2.com/research/sota/video-detail-captioning-on-vdc.md?metric=Short%20Component%20Score>): Higher is better; unit: SCALAR.

- [Background Component Score](<https://www.sota2.com/research/sota/video-detail-captioning-on-vdc.md?metric=Background%20Component%20Score>): Higher is better; unit: SCALAR.

- [Main Object Component Score](<https://www.sota2.com/research/sota/video-detail-captioning-on-vdc.md?metric=Main%20Object%20Component%20Score>): Higher is better; unit: SCALAR.

- [Detail Component Score](<https://www.sota2.com/research/sota/video-detail-captioning-on-vdc.md?metric=Detail%20Component%20Score>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/video-detail-captioning-on-vdc.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Camera Component Score | Result date | Report paper |
| --- | --- | --- | --- |
| SynPO | 1.8 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO | 1.79 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO | 1.78 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO-v3 | 1.75 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO | 1.75 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO-v2 | 1.74 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO | 1.74 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO-v1 | 1.72 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO-v5 | 1.57 | Not recorded | 68fa78fe1e209131cea7b893 |
| DPOP | 1.55 | Not recorded | 68fa78fe1e209131cea7b893 |
| KTO | 1.53 | Not recorded | 68fa78fe1e209131cea7b893 |
| SimPO | 1.52 | Not recorded | 68fa78fe1e209131cea7b893 |
| SynPO-v4 | 1.48 | Not recorded | 68fa78fe1e209131cea7b893 |
| SFT | 1.46 | Not recorded | 68fa78fe1e209131cea7b893 |
| SFT | 1.45 | Not recorded | 68fa78fe1e209131cea7b893 |
| DPO | 1.45 | Not recorded | 68fa78fe1e209131cea7b893 |
| IPO | 1.44 | Not recorded | 68fa78fe1e209131cea7b893 |
| DPO | 1.44 | Not recorded | 68fa78fe1e209131cea7b893 |
| DPO | 1.44 | Not recorded | 68fa78fe1e209131cea7b893 |
| SFT | 1.43 | Not recorded | 68fa78fe1e209131cea7b893 |
| CPO | 1.42 | Not recorded | 68fa78fe1e209131cea7b893 |
| DPO | 1.41 | Not recorded | 68fa78fe1e209131cea7b893 |
| SFT | 1.4 | Not recorded | 68fa78fe1e209131cea7b893 |
| DPO | 1.39 | Not recorded | 68fa78fe1e209131cea7b893 |
| SFT | 1.37 | Not recorded | 68fa78fe1e209131cea7b893 |
| Base | 1.26 | Not recorded | 68fa78fe1e209131cea7b893 |
| Base | 1.22 | Not recorded | 68fa78fe1e209131cea7b893 |
| Base | 1.14 | Not recorded | 68fa78fe1e209131cea7b893 |

### SynPO

Camera Component Score: 1.8. Result ID: 69c2958147f34ce924aaf9f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"InternVL2-8B","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SynPO

Camera Component Score: 1.79. Result ID: 69c2958147f34ce924aaf9e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Pandas-70M"}. This record does not assert independent reproduction.

### SynPO

Camera Component Score: 1.78. Result ID: 69c2958147f34ce924aaf9e2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SynPO-v3

Camera Component Score: 1.75. Result ID: 69c2958147f34ce924aaf9df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SynPO

Camera Component Score: 1.75. Result ID: 69c2958147f34ce924aaf9e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Charades"}. This record does not assert independent reproduction.

### SynPO-v2

Camera Component Score: 1.74. Result ID: 69c2958147f34ce924aaf9de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SynPO

Camera Component Score: 1.74. Result ID: 69c2958147f34ce924aaf9ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"LLaVA1.6-7B-video","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SynPO-v1

Camera Component Score: 1.72. Result ID: 69c2958147f34ce924aaf9dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SynPO-v5

Camera Component Score: 1.57. Result ID: 69c2958147f34ce924aaf9e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### DPOP

Camera Component Score: 1.55. Result ID: 69c2958147f34ce924aaf9d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74061e209131cea5f4d0.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### KTO

Camera Component Score: 1.53. Result ID: 69c2958147f34ce924aaf9da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75c61e209131cea69ebe.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SimPO

Camera Component Score: 1.52. Result ID: 69c2958147f34ce924aaf9dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a5e.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SynPO-v4

Camera Component Score: 1.48. Result ID: 69c2958147f34ce924aaf9e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SFT

Camera Component Score: 1.46. Result ID: 69c2958147f34ce924aaf9ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"InternVL2-8B","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SFT

Camera Component Score: 1.45. Result ID: 69c2958147f34ce924aaf9e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Pandas-70M"}. This record does not assert independent reproduction.

### DPO

Camera Component Score: 1.45. Result ID: 69c2958147f34ce924aaf9eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74511e209131cea6105d.md>)

Recorded evaluation configuration: {"Model Backbone":"LLaVA1.6-7B-video","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### IPO

Camera Component Score: 1.44. Result ID: 69c2958147f34ce924aaf9d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713c1e209131cea4ff94.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### DPO

Camera Component Score: 1.44. Result ID: 69c2958147f34ce924aaf9e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74511e209131cea6105d.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Pandas-70M"}. This record does not assert independent reproduction.

### DPO

Camera Component Score: 1.44. Result ID: 69c2958147f34ce924aaf9ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74511e209131cea6105d.md>)

Recorded evaluation configuration: {"Model Backbone":"InternVL2-8B","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SFT

Camera Component Score: 1.43. Result ID: 69c2958147f34ce924aaf9d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### CPO

Camera Component Score: 1.42. Result ID: 69c2958147f34ce924aaf9db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c31e.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### DPO

Camera Component Score: 1.41. Result ID: 69c2958147f34ce924aaf9e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74511e209131cea6105d.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Charades"}. This record does not assert independent reproduction.

### SFT

Camera Component Score: 1.4. Result ID: 69c2958147f34ce924aaf9e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Charades"}. This record does not assert independent reproduction.

### DPO

Camera Component Score: 1.39. Result ID: 69c2958147f34ce924aaf9d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74511e209131cea6105d.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### SFT

Camera Component Score: 1.37. Result ID: 69c2958147f34ce924aaf9ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"LLaVA1.6-7B-video","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### Base

Camera Component Score: 1.26. Result ID: 69c2958147f34ce924aaf9ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"InternVL2-8B","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### Base

Camera Component Score: 1.22. Result ID: 69c2958147f34ce924aaf9d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"AuroraCap","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

### Base

Camera Component Score: 1.14. Result ID: 69c2958147f34ce924aaf9e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78fe1e209131cea7b893.md>)

Recorded evaluation configuration: {"Model Backbone":"LLaVA1.6-7B-video","Fine-tuning Dataset":"Sharegpt4video"}. This record does not assert independent reproduction.

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