# Historical Image Dating on Historical color image dataset (test)

Source: [Historical Image Dating on Historical color image dataset (test)](<https://www.sota2.com/research/sota/historical-image-dating-on-historical-color-image-dataset-test>)

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

Data updated: 2026-02-26T05:27:51.183Z

Evaluation of historical image dating performance on the test split of the Historical color image dataset, measured using Accuracy and Mean Absolute Error (MAE).

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 | Historical Image Dating |
| Dataset (including any stated split) | Historical color image dataset (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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/historical-image-dating-on-historical-color-image-dataset-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [MAE](<https://www.sota2.com/research/sota/historical-image-dating-on-historical-color-image-dataset-test.md?metric=MAE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Classification + POE | 54.68 | Not recorded | 68fa699a1e209131cea22fd2 |
| CNNPOR | 50.12 | Not recorded | 68fa699a1e209131cea22fd2 |
| Ranking + POE | 50.01 | Not recorded | 68fa699a1e209131cea22fd2 |
| Classification | 48.94 | Not recorded | 68fa699a1e209131cea22fd2 |
| GP-DNNOR | 46.6 | Not recorded | 68fa699a1e209131cea22fd2 |
| D-Regression + POE | 46.04 | Not recorded | 68fa699a1e209131cea22fd2 |
| Palermo et al. | 44.92 | Not recorded | 68fa699a1e209131cea22fd2 |
| Ranking | 44.67 | Not recorded | 68fa699a1e209131cea22fd2 |
| D-Regression | 42.24 | Not recorded | 68fa699a1e209131cea22fd2 |

### Classification + POE

Accuracy: 54.68. Result ID: 698dc17a8b517eb4332389f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

[Implementation](<https://github.com/Li-Wanhua/POEs>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### CNNPOR

Accuracy: 50.12. Result ID: 698dc17a8b517eb4332389f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### Ranking + POE

Accuracy: 50.01. Result ID: 698dc17a8b517eb4332389fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

[Implementation](<https://github.com/Li-Wanhua/POEs>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### Classification

Accuracy: 48.94. Result ID: 698dc17a8b517eb4332389f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### GP-DNNOR

Accuracy: 46.6. Result ID: 698dc17a8b517eb4332389f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### D-Regression + POE

Accuracy: 46.04. Result ID: 698dc17a8b517eb4332389f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

[Implementation](<https://github.com/Li-Wanhua/POEs>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### Palermo et al.

Accuracy: 44.92. Result ID: 698dc17a8b517eb4332389f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### Ranking

Accuracy: 44.67. Result ID: 698dc17a8b517eb4332389f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

### D-Regression

Accuracy: 42.24. Result ID: 698dc17a8b517eb4332389f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fd2.md>)

Recorded evaluation configuration: {"Backbone":"VGG-16","Pre-training":"ImageNet","Evaluation Protocol":"ten-fold cross-validation"}. This record does not assert independent reproduction.

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