# Action Segmentation on YouTube Instructions (test) Source: [Action Segmentation on YouTube Instructions (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:52.688Z Evaluation of Action Segmentation performance on the test split of the YouTube Instructions dataset. 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 | Action Segmentation | | Dataset (including any stated split) | YouTube Instructions (test) | | Metric | F1 Score (%) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [F1 Score (%)](): Higher is better; unit: PERCENT. - [MoF](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score (%) | Result date | Report paper | | --- | --- | --- | --- | | DLCL | 45.4 | Not recorded | 68fa69d21e209131cea24663 | | LSTM+AL | 39.7 | Not recorded | 68fa69ad1e209131cea2348c | | LSTM-AL | 39.7 | Not recorded | 68fa69d21e209131cea24663 | | TOT+TCL | 32.9 | Not recorded | 68fa71091e209131cea4ecd4 | | UFSA | 32.4 | Not recorded | 68fa71091e209131cea4ecd4 | | ASAL | 32.1 | Not recorded | 68fa69ad1e209131cea2348c | | ASAL | 32.1 | Not recorded | 68fa71091e209131cea4ecd4 | | TOT | 30 | Not recorded | 68fa71091e209131cea4ecd4 | | VTE-UNET | 29.9 | Not recorded | 68fa69ad1e209131cea2348c | | VTE | 29.9 | Not recorded | 68fa71091e209131cea4ecd4 | | UDE | 29.6 | Not recorded | 68fa71091e209131cea4ecd4 | | CTE | 28.3 | Not recorded | 68fa69ad1e209131cea2348c | | CTE | 28.3 | Not recorded | 68fa71091e209131cea4ecd4 | | Mallow | 27 | Not recorded | 68fa69ad1e209131cea2348c | | Mallow | 27 | Not recorded | 68fa71091e209131cea4ecd4 | | Frank-Wolfe | 24.4 | Not recorded | 68fa69ad1e209131cea2348c | | Frank-Wolfe | 24.4 | Not recorded | 68fa71091e209131cea4ecd4 | ### DLCL F1 Score (%): 45.4. Result ID: 698deb2fffc3901de0998ddb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Video-based Hungarian matching":true,"Background frames":"included"}. This record does not assert independent reproduction. ### LSTM+AL F1 Score (%): 39.7. Result ID: 698dce4a8b517eb43323db56. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Supervision":"Unsupervised","Matching Strategy":"Per video Hungarian matching"}. This record does not assert independent reproduction. ### LSTM-AL F1 Score (%): 39.7. Result ID: 698deb2fffc3901de0998dda. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Video-based Hungarian matching":true,"Background frames":"included"}. This record does not assert independent reproduction. ### TOT+TCL F1 Score (%): 32.9. Result ID: 6991740f3a6c3148490845aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Temporal Contrastive Learning (TCL)":true}. This record does not assert independent reproduction. ### UFSA F1 Score (%): 32.4. Result ID: 6991740f3a6c3148490845ab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ASAL F1 Score (%): 32.1. Result ID: 698dce4a8b517eb43323db55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"Unsupervised","Matching Strategy":"Hungarian matching over all videos"}. This record does not assert independent reproduction. ### ASAL F1 Score (%): 32.1. Result ID: 6991740f3a6c3148490845a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TOT F1 Score (%): 30. Result ID: 6991740f3a6c3148490845a9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VTE-UNET F1 Score (%): 29.9. Result ID: 698dce4a8b517eb43323db54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"Unsupervised","Matching Strategy":"Hungarian matching over all videos"}. This record does not assert independent reproduction. ### VTE F1 Score (%): 29.9. Result ID: 6991740f3a6c3148490845a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UDE F1 Score (%): 29.6. Result ID: 6991740f3a6c3148490845a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CTE F1 Score (%): 28.3. Result ID: 698dce4a8b517eb43323db53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Supervision":"Unsupervised","Matching Strategy":"Hungarian matching over all videos"}. This record does not assert independent reproduction. ### CTE F1 Score (%): 28.3. Result ID: 6991740f3a6c3148490845a5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mallow F1 Score (%): 27. Result ID: 698dce4a8b517eb43323db52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"Unsupervised","Matching Strategy":"Hungarian matching over all videos"}. This record does not assert independent reproduction. ### Mallow F1 Score (%): 27. Result ID: 6991740f3a6c3148490845a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Frank-Wolfe F1 Score (%): 24.4. Result ID: 698dce4a8b517eb43323db51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Supervision":"Unsupervised","Matching Strategy":"Hungarian matching over all videos"}. This record does not assert independent reproduction. ### Frank-Wolfe F1 Score (%): 24.4. Result ID: 6991740f3a6c3148490845a3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.