# Visual Question Answering on COCOVQA zero-shot 2015

Source: [Visual Question Answering on COCOVQA zero-shot 2015](<https://www.sota2.com/research/sota/visual-question-answering-on-cocovqa-zero-shot-2015>)

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

Data updated: 2026-02-26T05:26:51.693Z

Evaluation of model performance on the zero-shot setting of the COCOVQA 2015 dataset for visual question answering, reporting metrics categorized by question type (e.g., Open-ended, Yes/No, Numerical).

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) | COCOVQA zero-shot 2015 |
| Metric | Acc (Open) |
| 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

- [Acc (Open)](<https://www.sota2.com/research/sota/visual-question-answering-on-cocovqa-zero-shot-2015.md?metric=Acc%20(Open)>): Higher is better; unit: PERCENT.

- [Acc (Numerical)](<https://www.sota2.com/research/sota/visual-question-answering-on-cocovqa-zero-shot-2015.md?metric=Acc%20(Numerical)>): Higher is better; unit: PERCENT.

- [Acc (Yes/No)](<https://www.sota2.com/research/sota/visual-question-answering-on-cocovqa-zero-shot-2015.md?metric=Acc%20(Yes%2FNo)>): Higher is better; unit: PERCENT.

- [Overall Acc](<https://www.sota2.com/research/sota/visual-question-answering-on-cocovqa-zero-shot-2015.md?metric=Overall%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc (Open) | Result date | Report paper |
| --- | --- | --- | --- |
| PSGTR | 29.03 | Not recorded | 68fa76ad1e209131cea6e652 |
| Pix2SG | 28.27 | Not recorded | 68fa76ad1e209131cea6e652 |
| IMP | 26.65 | Not recorded | 68fa76ad1e209131cea6e652 |

### PSGTR

Acc (Open): 29.03. Result ID: 69944a603a6c3148491c4ba3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e652.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d131e209131cea37790.md>)

[Implementation](<https://github.com/Jingkang50/OpenPSG>)

Recorded evaluation configuration: {"Location-Free":false}. This record does not assert independent reproduction.

### Pix2SG

Acc (Open): 28.27. Result ID: 69944a603a6c3148491c4ba4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e652.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e652.md>)

[Implementation](<https://github.com/egeozsoy/LF-SGG>)

Recorded evaluation configuration: {"Backbone":"ViT-L","Location-Free":true,"zero-shot":true}. This record does not assert independent reproduction.

### IMP

Acc (Open): 26.65. Result ID: 69944a603a6c3148491c4ba2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e652.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634d1e209131ce9fde50.md>)

Recorded evaluation configuration: {"Location-Free":false}. This record does not assert independent reproduction.

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