# Visual Question Answering on VQA-VS (IID)

Source: [Visual Question Answering on VQA-VS (IID)](<https://www.sota2.com/research/sota/visual-question-answering-on-vqa-vs-iid>)

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

Data updated: 2026-02-26T06:08:03.997Z

Evaluation of model performance on the VQA-VS dataset under IID conditions for visual question answering.

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 | Visual Question Answering |
| Dataset (including any stated split) | VQA-VS (IID) |
| Metric | VQA Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [VQA Score](<https://www.sota2.com/research/sota/visual-question-answering-on-vqa-vs-iid.md?metric=VQA%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | VQA Score | Result date | Report paper |
| --- | --- | --- | --- |
| I2M2 | 68.63 | Not recorded | 68fa76101e209131cea6b380 |
| Inter-modality modeling | 68.04 | Not recorded | 68fa76101e209131cea6b380 |
| Intra-modality modeling | 57.59 | Not recorded | 68fa76101e209131cea6b380 |
| Uni-modal (Text) | 43.78 | Not recorded | 68fa76101e209131cea6b380 |
| Uni-modal (Image) | 25.92 | Not recorded | 68fa76101e209131cea6b380 |

### I2M2

VQA Score: 68.63. Result ID: 699423713a6c3148491b5321.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b380.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b380.md>)

[Implementation](<https://github.com/divyam3897/multimodal_learning>)

Recorded evaluation configuration: {"INTRA I":"true","INTRA T":"true","INTER":"true"}. This record does not assert independent reproduction.

### Inter-modality modeling

VQA Score: 68.04. Result ID: 699423713a6c3148491b5320.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b380.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638a1e209131ce9ff617.md>)

Recorded evaluation configuration: {"INTRA I":"false","INTRA T":"false","INTER":"true"}. This record does not assert independent reproduction.

### Intra-modality modeling

VQA Score: 57.59. Result ID: 699423713a6c3148491b531f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b380.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61681e209131ce9f4271.md>)

Recorded evaluation configuration: {"INTRA I":"true","INTRA T":"true","INTER":"false"}. This record does not assert independent reproduction.

### Uni-modal (Text)

VQA Score: 43.78. Result ID: 699423713a6c3148491b531e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b380.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e011e209131cea3d5c4.md>)

[Implementation](<https://github.com/microsoft/FIBER>)

Recorded evaluation configuration: {"INTRA I":"false","INTRA T":"true","INTER":"false"}. This record does not assert independent reproduction.

### Uni-modal (Image)

VQA Score: 25.92. Result ID: 699423713a6c3148491b531d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b380.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e011e209131cea3d5c4.md>)

[Implementation](<https://github.com/microsoft/FIBER>)

Recorded evaluation configuration: {"INTRA I":"true","INTRA T":"false","INTER":"false"}. This record does not assert independent reproduction.

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