# Facial Expression Recognition on BAH 214 source subjects (10 target subjects)

Source: [Facial Expression Recognition on BAH 214 source subjects (10 target subjects)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects>)

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

Data updated: 2026-03-11T06:42:23.839Z

Evaluation of Facial Expression Recognition performance using the BAH 214 dataset, reporting results segmented by the 10 target subjects.

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 | Facial Expression Recognition |
| Dataset (including any stated split) | BAH 214 source subjects (10 target subjects) |
| Metric | Accuracy (Sub-1) |
| 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 (Sub-1)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-1)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-2)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-2)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-3)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-3)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-4)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-4)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-5)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-5)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-6)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-6)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-7)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-7)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-8)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-8)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-9)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-9)>): Higher is better; unit: PERCENT.

- [Accuracy (Sub-10)](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Accuracy%20(Sub-10)>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/facial-expression-recognition-on-bah-214-source-subjects-10-target-subjects.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Sub-1) | Result date | Report paper |
| --- | --- | --- | --- |
| Supervised fine-tuning | 96.2 | Not recorded | 68fa7aa91e209131cea8475a |
| SFDA-PFT | 61.52 | Not recorded | 68fa7aa91e209131cea8475a |
| SFIT | 56.83 | Not recorded | 68fa7aa91e209131cea8475a |
| DSFDA | 49.1 | Not recorded | 68fa7aa91e209131cea8475a |
| NRC | 48.72 | Not recorded | 68fa7aa91e209131cea8475a |
| SFDA-IT | 48.5 | Not recorded | 68fa7aa91e209131cea8475a |
| TPDS | 41.22 | Not recorded | 68fa7aa91e209131cea8475a |
| SHOT | 40.53 | Not recorded | 68fa7aa91e209131cea8475a |
| Source model (no adaptation) | 11.2 | Not recorded | 68fa7aa91e209131cea8475a |

### Supervised fine-tuning

Accuracy (Sub-1): 96.2. Result ID: 69b10d1e6dbb7075b95abe1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

Recorded evaluation configuration: {"Setting":"Oracle"}. This record does not assert independent reproduction.

### SFDA-PFT

Accuracy (Sub-1): 61.52. Result ID: 69b10d1e6dbb7075b95abe1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

Recorded evaluation configuration: {"Setting":"SFDA (data-based)"}. This record does not assert independent reproduction.

### SFIT

Accuracy (Sub-1): 56.83. Result ID: 69b10d1e6dbb7075b95abe19.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69e91e209131cea24d52.md>)

Recorded evaluation configuration: {"Setting":"SFDA (data-based)"}. This record does not assert independent reproduction.

### DSFDA

Accuracy (Sub-1): 49.1. Result ID: 69b10d1e6dbb7075b95abe18.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790b1e209131cea7bd97.md>)

Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction.

### NRC

Accuracy (Sub-1): 48.72. Result ID: 69b10d1e6dbb7075b95abe16.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b521e209131cea2da05.md>)

[Implementation](<https://github.com/Albert0147/SFDA_neighbors>)

Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction.

### SFDA-IT

Accuracy (Sub-1): 48.5. Result ID: 69b10d1e6dbb7075b95abe1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f31e209131cea25356.md>)

Recorded evaluation configuration: {"Setting":"SFDA (data-based)"}. This record does not assert independent reproduction.

### TPDS

Accuracy (Sub-1): 41.22. Result ID: 69b10d1e6dbb7075b95abe17.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction.

### SHOT

Accuracy (Sub-1): 40.53. Result ID: 69b10d1e6dbb7075b95abe15.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0e1e209131cea25d69.md>)

[Implementation](<https://github.com/tim-learn/SHOT>)

Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction.

### Source model (no adaptation)

Accuracy (Sub-1): 11.2. Result ID: 69b10d1e6dbb7075b95abe14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7aa91e209131cea8475a.md>)

Recorded evaluation configuration: {"Setting":"Source-only"}. This record does not assert independent reproduction.

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