# Video Question Answering on ActivityNet (A-Net)

Source: [Video Question Answering on ActivityNet (A-Net)](<https://www.sota2.com/research/sota/video-question-answering-on-activitynet-a-net>)

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

Data updated: 2026-03-11T08:53:52.893Z

Evaluation of Video Question Answering performance on the ActivityNet (A-Net) dataset, reporting Accuracy and Relative Average Performance.

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 | Video Question Answering |
| Dataset (including any stated split) | ActivityNet (A-Net) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-activitynet-a-net.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Relative Average Performance](<https://www.sota2.com/research/sota/video-question-answering-on-activitynet-a-net.md?metric=Relative%20Average%20Performance>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Video-LLaVA | 43.1 | Not recorded | 69b0f72c2d603e6de3e45f6d |
| PRUNESID | 43.1 | Not recorded | 69b0f72c2d603e6de3e45f6d |
| VisionZip | 43 | Not recorded | 69b0f72c2d603e6de3e45f6d |
| SparseVLM | 42.6 | Not recorded | 69b0f72c2d603e6de3e45f6d |
| FastV | 30.6 | Not recorded | 69b0f72c2d603e6de3e45f6d |

### Video-LLaVA

Accuracy: 43.1. Result ID: 69b12d9c6dbb7075b95bb43f.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72c2d603e6de3e45f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65534.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Video-LLaVA>)

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

### PRUNESID

Accuracy: 43.1. Result ID: 69b12d9c6dbb7075b95bb443.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72c2d603e6de3e45f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f72c2d603e6de3e45f6d.md>)

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

### VisionZip

Accuracy: 43. Result ID: 69b12d9c6dbb7075b95bb442.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72c2d603e6de3e45f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa760f1e209131cea6b33b.md>)

[Implementation](<https://github.com/dvlab-research/VisionZip>)

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

### SparseVLM

Accuracy: 42.6. Result ID: 69b12d9c6dbb7075b95bb441.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72c2d603e6de3e45f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79181e209131cea7c1b1.md>)

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

### FastV

Accuracy: 30.6. Result ID: 69b12d9c6dbb7075b95bb440.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72c2d603e6de3e45f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ae1e209131cea632b7.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.