# Facial Expression Recognition on SFEW 2.0 (test) Source: [Facial Expression Recognition on SFEW 2.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:51.853Z Evaluation of Facial Expression Recognition performance on the test split of the SFEW 2.0 dataset, typically measured by Accuracy. 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) | SFEW 2.0 (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | HDC†† | 61.6 | Not recorded | 68fa62d41e209131ce9fb6df | | CMU†† | 61.29 | Not recorded | 68fa62d41e209131ce9fb6df | | VGG-VD-16 | 59.41 | Not recorded | 68fa62d41e209131ce9fb6df | | DMUE | 58.34 | Not recorded | 68fa69b11e209131cea237a7 | | CMU\* | 58.06 | Not recorded | 68fa62d41e209131ce9fb6df | | HDC\* | 57.3 | Not recorded | 68fa62d41e209131ce9fb6df | | DMUE | 57.12 | Not recorded | 68fa69b11e209131cea237a7 | | RAN | 56.4 | Not recorded | 68fa69b11e209131cea237a7 | | MultiCNNs | 55.96 | Not recorded | 68fa69b11e209131cea237a7 | | VGG-M | 53.49 | Not recorded | 68fa62d41e209131ce9fb6df | | Island loss | 52.52 | Not recorded | 68fa69b11e209131cea237a7 | | Incept-ResV1 | 51.9 | Not recorded | 68fa69b11e209131cea237a7 | | IdentityCNN | 50.98 | Not recorded | 68fa69b11e209131cea237a7 | | AlexNet | 50.81 | Not recorded | 68fa62d41e209131ce9fb6df | | Resnet-50 | 45.97 | Not recorded | 68fa62d41e209131ce9fb6df | ### HDC†† Accuracy: 61.6. Result ID: 698be297ecace47ef55991d8. [Reporting paper]() Recorded evaluation configuration: {"Pretraining":"FER + TFD","ensemble":true}. This record does not assert independent reproduction. ### CMU†† Accuracy: 61.29. Result ID: 698be297ecace47ef55991d7. [Reporting paper]() Recorded evaluation configuration: {"Pretraining":"FER combined","ensemble":true}. This record does not assert independent reproduction. ### VGG-VD-16 Accuracy: 59.41. Result ID: 698be297ecace47ef55991d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining":"VGGFaces+FER"}. This record does not assert independent reproduction. ### DMUE Accuracy: 58.34. Result ID: 698dd4dbffc3901de098ed5e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50IBN"}. This record does not assert independent reproduction. ### CMU\* Accuracy: 58.06. Result ID: 698be297ecace47ef55991d5. [Reporting paper]() Recorded evaluation configuration: {"Pretraining":"FER combined","best\_single\_CNN":true}. This record does not assert independent reproduction. ### HDC\* Accuracy: 57.3. Result ID: 698be297ecace47ef55991d6. [Reporting paper]() Recorded evaluation configuration: {"Pretraining":"FER + TFD","best\_single\_CNN":true}. This record does not assert independent reproduction. ### DMUE Accuracy: 57.12. Result ID: 698dd4dbffc3901de098ed5d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### RAN Accuracy: 56.4. Result ID: 698dd4dbffc3901de098ed5c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MultiCNNs Accuracy: 55.96. Result ID: 698dd4dbffc3901de098ed5b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VGG-M Accuracy: 53.49. Result ID: 698be297ecace47ef55991d2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining":"VGGFaces+FER"}. This record does not assert independent reproduction. ### Island loss Accuracy: 52.52. Result ID: 698dd4dbffc3901de098ed59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Incept-ResV1 Accuracy: 51.9. Result ID: 698dd4dbffc3901de098ed5a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### IdentityCNN Accuracy: 50.98. Result ID: 698dd4dbffc3901de098ed58. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AlexNet Accuracy: 50.81. Result ID: 698be297ecace47ef55991d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining":"VGGFaces+FER"}. This record does not assert independent reproduction. ### Resnet-50 Accuracy: 45.97. Result ID: 698be297ecace47ef55991d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining":"VGGFaces+FER"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.