# Visual Question Answering on KVQA (Original (ORG))

Source: [Visual Question Answering on KVQA (Original (ORG))](<https://www.sota2.com/research/sota/visual-question-answering-on-kvqa-original-org>)

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

Data updated: 2026-02-26T05:28:15.661Z

Evaluation of model performance on the original split of the KVQA dataset for visual question answering capabilities.

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) | KVQA (Original (ORG)) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/visual-question-answering-on-kvqa-original-org.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Hypergraph Transformer | 62 | Not recorded | 68fa6c571e209131cea3367d |
| Transformer | 60.4 | Not recorded | 68fa6c571e209131cea3367d |
| BAN | 59.6 | Not recorded | 68fa6c571e209131cea3367d |
| Transformer | 57.5 | Not recorded | 68fa6c571e209131cea3367d |
| MemNN† | 54 | Not recorded | 68fa6c571e209131cea3367d |
| HAN | 53.4 | Not recorded | 68fa6c571e209131cea3367d |
| GGNN | 50.9 | Not recorded | 68fa6c571e209131cea3367d |
| MemNN | 50.2 | Not recorded | 68fa6c571e209131cea3367d |
| GCN | 48.9 | Not recorded | 68fa6c571e209131cea3367d |
| BLSTM | 48 | Not recorded | 68fa6c571e209131cea3367d |

### Hypergraph Transformer

Accuracy: 62. Result ID: 698f05633a6c314849f4d874.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Implementation](<https://github.com/yujungheo/kbvqa-public>)

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

### Transformer

Accuracy: 60.4. Result ID: 698f05633a6c314849f4d873.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"mechanism":"SA+GA"}. This record does not assert independent reproduction.

### BAN

Accuracy: 59.6. Result ID: 698f05633a6c314849f4d871.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64fd1e209131cea07a2c.md>)

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

### Transformer

Accuracy: 57.5. Result ID: 698f05633a6c314849f4d872.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"mechanism":"SA"}. This record does not assert independent reproduction.

### MemNN†

Accuracy: 54. Result ID: 698f05633a6c314849f4d86f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622f1e209131ce9f80a6.md>)

[Implementation](<https://github.com/facebook/MemNN>)

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

### HAN

Accuracy: 53.4. Result ID: 698f05633a6c314849f4d870.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

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

### GGNN

Accuracy: 50.9. Result ID: 698f05633a6c314849f4d86e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63a31e209131ce9ffef4.md>)

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

### MemNN

Accuracy: 50.2. Result ID: 698f05633a6c314849f4d86c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622f1e209131ce9f80a6.md>)

[Implementation](<https://github.com/facebook/MemNN>)

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

### GCN

Accuracy: 48.9. Result ID: 698f05633a6c314849f4d86d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa631d1e209131ce9fce45.md>)

[Implementation](<https://github.com/tkipf/gcn>)

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

### BLSTM

Accuracy: 48. Result ID: 698f05633a6c314849f4d86b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

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.