# Visual emotion distribution learning on Abstract Paintings

Source: [Visual emotion distribution learning on Abstract Paintings](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings>)

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

Data updated: 2026-02-26T05:39:06.770Z

Evaluation of models on learning the visual emotion distribution using the Abstract Paintings dataset, measured using distribution similarity metrics like Chebyshev distance and KL divergence.

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 emotion distribution learning |
| Dataset (including any stated split) | Abstract Paintings |
| Metric | Chebyshev Distance |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [Chebyshev Distance](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings.md?metric=Chebyshev%20Distance>): Lower is better; unit: SCALAR.

- [Clark Distance](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings.md?metric=Clark%20Distance>): Lower is better; unit: SCALAR.

- [Canberra Metric](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings.md?metric=Canberra%20Metric>): Lower is better; unit: SCALAR.

- [KL Divergence](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings.md?metric=KL%20Divergence>): Lower is better; unit: SCALAR.

- [Cosine Similarity](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings.md?metric=Cosine%20Similarity>): Higher is better; unit: SCALAR.

- [Intersection Similarity](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings.md?metric=Intersection%20Similarity>): Higher is better; unit: PERCENT.

- [Average Rank](<https://www.sota2.com/research/sota/visual-emotion-distribution-learning-on-abstract-paintings.md?metric=Average%20Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Chebyshev Distance | Result date | Report paper |
| --- | --- | --- | --- |
| Emotion Circle | 0.226 | Not recorded | 68fa6a3b1e209131cea26d4e |
| ACPNN | 0.234 | Not recorded | 68fa6a3b1e209131cea26d4e |
| AA-KNN | 0.245 | Not recorded | 68fa6a3b1e209131cea26d4e |
| SA-IIS | 0.296 | Not recorded | 68fa6a3b1e209131cea26d4e |
| AA-BP | 0.297 | Not recorded | 68fa6a3b1e209131cea26d4e |
| PT-SVM | 0.298 | Not recorded | 68fa6a3b1e209131cea26d4e |
| PT-Bayes | 0.36 | Not recorded | 68fa6a3b1e209131cea26d4e |
| SA-BFGS | 0.472 | Not recorded | 68fa6a3b1e209131cea26d4e |

### Emotion Circle

Chebyshev Distance: 0.226. Result ID: 698e2109ffc3901de09b029c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

Recorded evaluation configuration: {"Category":"CNN-based"}. This record does not assert independent reproduction.

### ACPNN

Chebyshev Distance: 0.234. Result ID: 698e2109ffc3901de09b029b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

Recorded evaluation configuration: {"Category":"CNN-based"}. This record does not assert independent reproduction.

### AA-KNN

Chebyshev Distance: 0.245. Result ID: 698e2109ffc3901de09b0297.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f935c.md>)

Recorded evaluation configuration: {"Category":"AA"}. This record does not assert independent reproduction.

### SA-IIS

Chebyshev Distance: 0.296. Result ID: 698e2109ffc3901de09b0299.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f935c.md>)

Recorded evaluation configuration: {"Category":"SA"}. This record does not assert independent reproduction.

### AA-BP

Chebyshev Distance: 0.297. Result ID: 698e2109ffc3901de09b0298.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f935c.md>)

Recorded evaluation configuration: {"Category":"AA"}. This record does not assert independent reproduction.

### PT-SVM

Chebyshev Distance: 0.298. Result ID: 698e2109ffc3901de09b0296.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f935c.md>)

Recorded evaluation configuration: {"Category":"PT"}. This record does not assert independent reproduction.

### PT-Bayes

Chebyshev Distance: 0.36. Result ID: 698e2109ffc3901de09b0295.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f935c.md>)

Recorded evaluation configuration: {"Category":"PT"}. This record does not assert independent reproduction.

### SA-BFGS

Chebyshev Distance: 0.472. Result ID: 698e2109ffc3901de09b029a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f935c.md>)

Recorded evaluation configuration: {"Category":"SA"}. This record does not assert independent reproduction.

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