# Video Question Answering on Causal-VidQA 1.0 (test)

Source: [Video Question Answering on Causal-VidQA 1.0 (test)](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test>)

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

Data updated: 2026-02-26T05:26:58.108Z

Evaluation of model performance on the test split of the Causal-VidQA 1.0 dataset for Video Question Answering tasks, reporting accuracy metrics broken down by reasoning type (e.g., Acc@D, Acc@E, Acc@P, Acc@C).

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) | Causal-VidQA 1.0 (test) |
| Metric | Acc@P |
| 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

- [Acc@P](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40P>): Higher is better; unit: PERCENT.

- [Acc@D (Q-A)](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40D%20(Q-A)>): Higher is better; unit: PERCENT.

- [Acc@D (Q-\>R)](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40D%20(Q-%3ER)>): Higher is better; unit: PERCENT.

- [Acc@D (Q-\>AR)](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40D%20(Q-%3EAR)>): Higher is better; unit: PERCENT.

- [Acc@E (Q-A)](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40E%20(Q-A)>): Higher is better; unit: PERCENT.

- [Acc@E (Q-\>R)](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40E%20(Q-%3ER)>): Higher is better; unit: PERCENT.

- [Acc@E (Q-\>AR)](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40E%20(Q-%3EAR)>): Higher is better; unit: PERCENT.

- [Acc@C](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40C>): Higher is better; unit: PERCENT.

- [Acc@All](<https://www.sota2.com/research/sota/video-question-answering-on-causal-vidqa-1-0-test.md?metric=Acc%40All>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc@P | Result date | Report paper |
| --- | --- | --- | --- |
| CoVGT | 74.36 | Not recorded | 68fa6ffe1e209131cea48621 |
| CoVGT | 73.46 | Not recorded | 68fa6ffe1e209131cea48621 |
| RoI+RoBERTa\* | 70.1 | Not recorded | 68fa6ffe1e209131cea48621 |
| B2A | 66.21 | Not recorded | 68fa6ffe1e209131cea48621 |
| BlindQA\* | 64.65 | Not recorded | 68fa6ffe1e209131cea48621 |

### CoVGT

Acc@P: 74.36. Result ID: 6990f3ea3a6c314849048d6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ffe1e209131cea48621.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ffe1e209131cea48621.md>)

[Implementation](<https://github.com/doc-doc/CoVGT>)

Recorded evaluation configuration: {"Video":"R, F","Text":"RoBERTa","Pre-training":"True"}. This record does not assert independent reproduction.

### CoVGT

Acc@P: 73.46. Result ID: 6990f3ea3a6c314849048d6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ffe1e209131cea48621.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ffe1e209131cea48621.md>)

[Implementation](<https://github.com/doc-doc/CoVGT>)

Recorded evaluation configuration: {"Video":"R, F","Text":"RoBERTa"}. This record does not assert independent reproduction.

### RoI+RoBERTa\*

Acc@P: 70.1. Result ID: 6990f3ea3a6c314849048d6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ffe1e209131cea48621.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Video":"R","Text":"RoBERTa"}. This record does not assert independent reproduction.

### B2A

Acc@P: 66.21. Result ID: 6990f3ea3a6c314849048d6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ffe1e209131cea48621.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea2494f.md>)

Recorded evaluation configuration: {"Video":"E, C","Text":"BERT"}. This record does not assert independent reproduction.

### BlindQA\*

Acc@P: 64.65. Result ID: 6990f3ea3a6c314849048d6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ffe1e209131cea48621.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Video":null,"Text":"RoBERTa"}. This record does not assert independent reproduction.

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