# Video Question Answering on TGIF-QA Action original (test)

Source: [Video Question Answering on TGIF-QA Action original (test)](<https://www.sota2.com/research/sota/video-question-answering-on-tgif-qa-action-original-test>)

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

Data updated: 2026-02-26T05:29:00.233Z

Evaluation of model performance on the test split of the TGIF-QA Action original dataset for Video Question Answering tasks, reporting accuracy metrics.

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) | TGIF-QA Action original (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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-tgif-qa-action-original-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| VGT | 95 | Not recorded | 68fa6ffe1e209131cea48621 |
| CoVGT | 94.7 | Not recorded | 68fa6ffe1e209131cea48621 |
| MERLOT | 94 | Not recorded | 68fa6ffe1e209131cea48621 |
| VGT (PT) | 93.1 | Not recorded | 68fa6ffe1e209131cea48621 |
| CoVGT (PT) | 91.3 | Not recorded | 68fa6ffe1e209131cea48621 |
| MASN | 84.4 | Not recorded | 68fa6ffe1e209131cea48621 |
| MHN | 83.5 | Not recorded | 68fa6ffe1e209131cea48621 |
| ClipBERT | 82.8 | Not recorded | 68fa6ffe1e209131cea48621 |
| PGAT | 80.6 | Not recorded | 68fa6ffe1e209131cea48621 |
| SiaSRea | 79.7 | Not recorded | 68fa6ffe1e209131cea48621 |
| HAIR | 77.8 | Not recorded | 68fa6ffe1e209131cea48621 |
| HQGA | 76.9 | Not recorded | 68fa6ffe1e209131cea48621 |
| B2A | 75.9 | Not recorded | 68fa6ffe1e209131cea48621 |
| HGA | 75.4 | Not recorded | 68fa6ffe1e209131cea48621 |
| HCRN | 75 | Not recorded | 68fa6ffe1e209131cea48621 |
| HOSTR | 75 | Not recorded | 68fa6ffe1e209131cea48621 |
| LGCN | 74.3 | Not recorded | 68fa6ffe1e209131cea48621 |

### VGT

Accuracy: 95. Result ID: 6990f3ea3a6c314849048d1a.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a911e209131cea28ec2.md>)

[Implementation](<https://antoyang.github.io/just-ask.html>)

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"BERT"}. This record does not assert independent reproduction.

### CoVGT

Accuracy: 94.7. Result ID: 6990f3ea3a6c314849048d1c.

[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: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"RoBERTa"}. This record does not assert independent reproduction.

### MERLOT

Accuracy: 94. Result ID: 6990f3ea3a6c314849048d19.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0f1e209131cea2bd51.md>)

[Implementation](<https://rowanzellers.com/merlot>)

Recorded evaluation configuration: {"Pretrain Dataset":"YT, CC","Pretrain Size":"183M","Text Encoder":"BERT"}. This record does not assert independent reproduction.

### VGT (PT)

Accuracy: 93.1. Result ID: 6990f3ea3a6c314849048d1b.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1a1e209131cea37c43.md>)

[Implementation](<https://github.com/sail-sg/VGT>)

Recorded evaluation configuration: {"Pretrain Dataset":"WV","Pretrain Size":"0.18M","Text Encoder":"BERT"}. This record does not assert independent reproduction.

### CoVGT (PT)

Accuracy: 91.3. Result ID: 6990f3ea3a6c314849048d1d.

[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: {"Pretrain Dataset":"WV","Pretrain Size":"0.18M","Text Encoder":"RoBERTa"}. This record does not assert independent reproduction.

### MASN

Accuracy: 84.4. Result ID: 6990f3ea3a6c314849048d15.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3d1e209131cea26e78.md>)

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### MHN

Accuracy: 83.5. Result ID: 6990f3ea3a6c314849048d16.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c7a1e209131cea342f0.md>)

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### ClipBERT

Accuracy: 82.8. Result ID: 6990f3ea3a6c314849048d17.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa694e1e209131cea216c8.md>)

[Implementation](<https://github.com/jayleicn/ClipBERT>)

Recorded evaluation configuration: {"Pretrain Dataset":"VG, COCO","Pretrain Size":"None","Text Encoder":"BERT"}. This record does not assert independent reproduction.

### PGAT

Accuracy: 80.6. Result ID: 6990f3ea3a6c314849048d14.

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

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### SiaSRea

Accuracy: 79.7. Result ID: 6990f3ea3a6c314849048d18.

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

Recorded evaluation configuration: {"Pretrain Dataset":"VG, COCO","Pretrain Size":"None","Text Encoder":"BERT"}. This record does not assert independent reproduction.

### HAIR

Accuracy: 77.8. Result ID: 6990f3ea3a6c314849048d12.

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

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### HQGA

Accuracy: 76.9. Result ID: 6990f3ea3a6c314849048d13.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea337c4.md>)

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"BERT"}. This record does not assert independent reproduction.

### B2A

Accuracy: 75.9. Result ID: 6990f3ea3a6c314849048d10.

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

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

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### HGA

Accuracy: 75.4. Result ID: 6990f3ea3a6c314849048d0e.

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

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### HCRN

Accuracy: 75. Result ID: 6990f3ea3a6c314849048d0f.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa67351e209131cea14bfd.md>)

[Implementation](<https://github.com/thaolmk54/hcrn-videoqa>)

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### HOSTR

Accuracy: 75. Result ID: 6990f3ea3a6c314849048d11.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a951e209131cea290f2.md>)

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

### LGCN

Accuracy: 74.3. Result ID: 6990f3ea3a6c314849048d0d.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa68321e209131cea1aac7.md>)

Recorded evaluation configuration: {"Pretrain Dataset":"None","Pretrain Size":"None","Text Encoder":"GloVe"}. This record does not assert independent reproduction.

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