# Dense Video Object Captioning on VidSTG

Source: [Dense Video Object Captioning on VidSTG](<https://www.sota2.com/research/sota/dense-video-object-captioning-on-vidstg>)

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

Data updated: 2026-06-01T09:17:55.139Z

Evaluation of Dense Video Object Captioning performance on the VidSTG dataset, measured using metrics CapA, DetA, AssA, and CHOTA.

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 | Dense Video Object Captioning |
| Dataset (including any stated split) | VidSTG |
| Metric | CapA Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [CapA Score](<https://www.sota2.com/research/sota/dense-video-object-captioning-on-vidstg.md?metric=CapA%20Score>): Higher is better; unit: PERCENT.

- [DetA Score](<https://www.sota2.com/research/sota/dense-video-object-captioning-on-vidstg.md?metric=DetA%20Score>): Higher is better; unit: PERCENT.

- [AssA Score](<https://www.sota2.com/research/sota/dense-video-object-captioning-on-vidstg.md?metric=AssA%20Score>): Higher is better; unit: PERCENT.

- [CHOTA Score](<https://www.sota2.com/research/sota/dense-video-object-captioning-on-vidstg.md?metric=CHOTA%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CapA Score | Result date | Report paper |
| --- | --- | --- | --- |
| CaptionFormer | 55.4 | Not recorded | 68fa7c2a1e209131cea8ccaa |
| CaptionFormer | 51 | Not recorded | 68fa7c2a1e209131cea8ccaa |
| CaptionFormer | 50.1 | Not recorded | 68fa7c2a1e209131cea8ccaa |
| CaptionFormer | 44.3 | Not recorded | 68fa7c2a1e209131cea8ccaa |
| OW-VISCaptor | 43.9 | Not recorded | 68fa7c2a1e209131cea8ccaa |
| DVOC-DS | 39.7 | Not recorded | 68fa7c2a1e209131cea8ccaa |
| OVFormer | 12.8 | Not recorded | 68fa7c2a1e209131cea8ccaa |
| Gemini-1.5-flash | 6.4 | Not recorded | 68fa7c2a1e209131cea8ccaa |

### CaptionFormer

CapA Score: 55.4. Result ID: 6a1d4e29fbc373592c16c756.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

Recorded evaluation configuration: {"Pretraining set":"COCO + LVIScap + LV-VIScap","temporal aggregation":"true"}. This record does not assert independent reproduction.

### CaptionFormer

CapA Score: 51. Result ID: 6a1d4e29fbc373592c16c755.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

Recorded evaluation configuration: {"Pretraining set":"COCO + LVIScap + LV-VIScap"}. This record does not assert independent reproduction.

### CaptionFormer

CapA Score: 50.1. Result ID: 6a1d4e29fbc373592c16c754.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

Recorded evaluation configuration: {"Pretraining set":"COCO + VG + SMIT + AugCOCO"}. This record does not assert independent reproduction.

### CaptionFormer

CapA Score: 44.3. Result ID: 6a1d4e29fbc373592c16c752.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

Recorded evaluation configuration: {"Pretraining set":"COCO"}. This record does not assert independent reproduction.

### OW-VISCaptor

CapA Score: 43.9. Result ID: 6a1d4e29fbc373592c16c751.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b71e209131cea74ef2.md>)

[Implementation](<https://anwesachoudhuri.github.io/OpenWorldVISCap/>)

Recorded evaluation configuration: {"Pretraining set":"COCO"}. This record does not assert independent reproduction.

### DVOC-DS

CapA Score: 39.7. Result ID: 6a1d4e29fbc373592c16c753.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75311e209131cea664d4.md>)

Recorded evaluation configuration: {"Pretraining set":"COCO + VG + SMIT + AugCOCO"}. This record does not assert independent reproduction.

### OVFormer

CapA Score: 12.8. Result ID: 6a1d4e29fbc373592c16c750.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa740d1e209131cea5f796.md>)

Recorded evaluation configuration: {"Pretraining set":"LVIS + LV-VIS"}. This record does not assert independent reproduction.

### Gemini-1.5-flash

CapA Score: 6.4. Result ID: 6a1d4e29fbc373592c16c74f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c2a1e209131cea8ccaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: {"Pretraining set":"-"}. This record does not assert independent reproduction.

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