# Dense Captioning on VG 1.2 (test)

Source: [Dense Captioning on VG 1.2 (test)](<https://www.sota2.com/research/sota/dense-captioning-on-vg-1-2-test>)

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

Data updated: 2026-02-26T05:22:50.228Z

Evaluation of Dense Captioning performance on the test split of Visual Genome version 1.2.

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 captioning |
| Dataset (including any stated split) | VG 1.2 (test) |
| Metric | AP |
| 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

- [AP](<https://www.sota2.com/research/sota/dense-captioning-on-vg-1-2-test.md?metric=AP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| DetCLIPv3 | 19.7 | Not recorded | 68fa72db1e209131cea58f4c |
| DetCLIPv3 | 18.4 | Not recorded | 68fa72db1e209131cea58f4c |
| GRIT | 15.5 | Not recorded | 68fa72db1e209131cea58f4c |
| CapDet | 15.4 | Not recorded | 68fa72db1e209131cea58f4c |
| TDC+ROCSU | 11.9 | Not recorded | 68fa72db1e209131cea58f4c |
| CAG-Net | 10.5 | Not recorded | 68fa72db1e209131cea58f4c |
| COCG | 10.4 | Not recorded | 68fa72db1e209131cea58f4c |
| JIVC | 10 | Not recorded | 68fa72db1e209131cea58f4c |

### DetCLIPv3

AP: 19.7. Result ID: 69929def3a6c314849102f5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

Recorded evaluation configuration: {"Backbone":"Swin-L"}. This record does not assert independent reproduction.

### DetCLIPv3

AP: 18.4. Result ID: 69929def3a6c314849102f59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

Recorded evaluation configuration: {"Backbone":"Swin-T"}. This record does not assert independent reproduction.

### GRIT

AP: 15.5. Result ID: 69929def3a6c314849102f58.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e231e209131cea3e161.md>)

[Implementation](<https://github.com/JialianW/GRiT>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CapDet

AP: 15.4. Result ID: 69929def3a6c314849102f57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ec31e209131cea41dc0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TDC+ROCSU

AP: 11.9. Result ID: 69929def3a6c314849102f56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CAG-Net

AP: 10.5. Result ID: 69929def3a6c314849102f55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa658f1e209131cea0b2a8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### COCG

AP: 10.4. Result ID: 69929def3a6c314849102f54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### JIVC

AP: 10. Result ID: 69929def3a6c314849102f53.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72db1e209131cea58f4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62311e209131ce9f8239.md>)

[Implementation](<https://github.com/qassemoquab/stnbhwd>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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