# Event-based Visual Question Answering on EvQA

Source: [Event-based Visual Question Answering on EvQA](<https://www.sota2.com/research/sota/event-based-visual-question-answering-on-evqa>)

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

Data updated: 2026-02-26T06:07:25.271Z

Evaluation of model performance on the EvQA dataset for event-based visual question answering, reporting total accuracy broken down by temporal response bins.

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 | Event-based Visual Question Answering |
| Dataset (including any stated split) | EvQA |
| Metric | Total Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Total Accuracy](<https://www.sota2.com/research/sota/event-based-visual-question-answering-on-evqa.md?metric=Total%20Accuracy>): Higher is better; unit: PERCENT.

- [Accuracy (\<0.5s)](<https://www.sota2.com/research/sota/event-based-visual-question-answering-on-evqa.md?metric=Accuracy%20(%3C0.5s)>): Higher is better; unit: PERCENT.

- [Accuracy (0.5-10s)](<https://www.sota2.com/research/sota/event-based-visual-question-answering-on-evqa.md?metric=Accuracy%20(0.5-10s)>): Higher is better; unit: PERCENT.

- [Accuracy (\>10s)](<https://www.sota2.com/research/sota/event-based-visual-question-answering-on-evqa.md?metric=Accuracy%20(%3E10s)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Total Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FRT | 0.673 | Not recorded | 693f95ea6cfd488761a818ba |
| ART | 0.463 | Not recorded | 693f95ea6cfd488761a818ba |
| EventGPT | 0.315 | Not recorded | 693f95ea6cfd488761a818ba |

### FRT

Total Accuracy: 0.673. Result ID: 699854bc5698665ec4b2a379.

[Reporting paper](<https://www.sota2.com/research/paper/693f95ea6cfd488761a818ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693f95ea6cfd488761a818ba.md>)

Recorded evaluation configuration: {"Size":"2B","FPS":"24"}. This record does not assert independent reproduction.

### ART

Total Accuracy: 0.463. Result ID: 699854bc5698665ec4b2a37a.

[Reporting paper](<https://www.sota2.com/research/paper/693f95ea6cfd488761a818ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693f95ea6cfd488761a818ba.md>)

Recorded evaluation configuration: {"Size":"2B"}. This record does not assert independent reproduction.

### EventGPT

Total Accuracy: 0.315. Result ID: 699854bc5698665ec4b2a378.

[Reporting paper](<https://www.sota2.com/research/paper/693f95ea6cfd488761a818ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76051e209131cea6af75.md>)

Recorded evaluation configuration: {"Size":"7B","Sequence Truncation":"0.1s"}. This record does not assert independent reproduction.

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