# Facial Expression Recognition on Aff-Wild2 (10 target subjects) Source: [Facial Expression Recognition on Aff-Wild2 (10 target subjects)]() Collection index: [llms.txt]() Data updated: 2026-03-11T06:42:23.946Z Evaluation of Facial Expression Recognition performance on the Aff-Wild2 dataset, specifically reporting results across 10 distinct 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) | Aff-Wild2 (10 target subjects) | | Metric | Accuracy (Subject 1) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 (Subject 1)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 2)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 3)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 4)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 5)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 6)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 7)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 8)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 9)](): Higher is better; unit: PERCENT. - [Accuracy (Subject 10)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Subject 1) | Result date | Report paper | | --- | --- | --- | --- | | Fine-tune | 98.9 | Not recorded | 68fa7aa91e209131cea8475a | | Supervised fine-tuning | 91.93 | Not recorded | 68fa7aa91e209131cea8475a | | SFDA-PFT | 60.83 | Not recorded | 68fa7aa91e209131cea8475a | | SFDA-IT | 59.63 | Not recorded | 68fa7aa91e209131cea8475a | | SFIT | 58.42 | Not recorded | 68fa7aa91e209131cea8475a | | DSFDA | 58.31 | Not recorded | 68fa7aa91e209131cea8475a | | SFDA-PFT | 52.66 | Not recorded | 68fa7aa91e209131cea8475a | | SFDA-IT | 49.3 | Not recorded | 68fa7aa91e209131cea8475a | | SFIT | 48.43 | Not recorded | 68fa7aa91e209131cea8475a | | TPDS | 47.62 | Not recorded | 68fa7aa91e209131cea8475a | | SHOT | 45 | Not recorded | 68fa7aa91e209131cea8475a | | NRC | 43.77 | Not recorded | 68fa7aa91e209131cea8475a | | DSFDA | 37.26 | Not recorded | 68fa7aa91e209131cea8475a | | TPDS | 36.69 | Not recorded | 68fa7aa91e209131cea8475a | | NRC | 34.24 | Not recorded | 68fa7aa91e209131cea8475a | | SHOT | 33.77 | Not recorded | 68fa7aa91e209131cea8475a | | Source model | 24.5 | Not recorded | 68fa7aa91e209131cea8475a | | Source model (no adaptation) | 18.7 | Not recorded | 68fa7aa91e209131cea8475a | ### Fine-tune Accuracy (Subject 1): 98.9. Result ID: 69b10d1e6dbb7075b95abe4e. [Reporting paper]() Recorded evaluation configuration: {"Setting":"Oracle","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Supervised fine-tuning Accuracy (Subject 1): 91.93. Result ID: 69b10d1e6dbb7075b95abe33. [Reporting paper]() Recorded evaluation configuration: {"Setting":"Oracle"}. This record does not assert independent reproduction. ### SFDA-PFT Accuracy (Subject 1): 60.83. Result ID: 69b10d1e6dbb7075b95abe4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (data-based)","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SFDA-IT Accuracy (Subject 1): 59.63. Result ID: 69b10d1e6dbb7075b95abe4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (data-based)","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SFIT Accuracy (Subject 1): 58.42. Result ID: 69b10d1e6dbb7075b95abe4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (data-based)","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DSFDA Accuracy (Subject 1): 58.31. Result ID: 69b10d1e6dbb7075b95abe4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SFDA-PFT Accuracy (Subject 1): 52.66. Result ID: 69b10d1e6dbb7075b95abe32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (data-based)"}. This record does not assert independent reproduction. ### SFDA-IT Accuracy (Subject 1): 49.3. Result ID: 69b10d1e6dbb7075b95abe31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (data-based)"}. This record does not assert independent reproduction. ### SFIT Accuracy (Subject 1): 48.43. Result ID: 69b10d1e6dbb7075b95abe30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (data-based)"}. This record does not assert independent reproduction. ### TPDS Accuracy (Subject 1): 47.62. Result ID: 69b10d1e6dbb7075b95abe49. [Reporting paper]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SHOT Accuracy (Subject 1): 45. Result ID: 69b10d1e6dbb7075b95abe47. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### NRC Accuracy (Subject 1): 43.77. Result ID: 69b10d1e6dbb7075b95abe48. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DSFDA Accuracy (Subject 1): 37.26. Result ID: 69b10d1e6dbb7075b95abe2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction. ### TPDS Accuracy (Subject 1): 36.69. Result ID: 69b10d1e6dbb7075b95abe2e. [Reporting paper]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction. ### NRC Accuracy (Subject 1): 34.24. Result ID: 69b10d1e6dbb7075b95abe2d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction. ### SHOT Accuracy (Subject 1): 33.77. Result ID: 69b10d1e6dbb7075b95abe2c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setting":"SFDA (model-based)"}. This record does not assert independent reproduction. ### Source model Accuracy (Subject 1): 24.5. Result ID: 69b10d1e6dbb7075b95abe46. [Reporting paper]() Recorded evaluation configuration: {"Setting":"Source-only","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Source model (no adaptation) Accuracy (Subject 1): 18.7. Result ID: 69b10d1e6dbb7075b95abe2b. [Reporting paper]() 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.