# Action Recognition on EPIC-KITCHENS 1 (S1 Seen kitchens) Source: [Action Recognition on EPIC-KITCHENS 1 (S1 Seen kitchens)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:16.207Z Evaluation of Action Recognition performance on the EPIC-KITCHENS 1 (S1 Seen kitchens) split, measured using Top-1/Top-5 Accuracy, Precision, and Recall across Verb, Noun, and Action predictions. 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 Recognition | | Dataset (including any stated split) | EPIC-KITCHENS 1 (S1 Seen kitchens) | | Metric | Top-1 Accuracy (Verb) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 31 of 31 | | 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 - [Top-1 Accuracy (Verb)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Noun)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Action)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (Verb)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (Noun)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (Action)](): Higher is better; unit: PERCENT. - [Precision (Verb)](): Higher is better; unit: PERCENT. - [Precision (Noun)](): Higher is better; unit: PERCENT. - [Precision (Action)](): Higher is better; unit: PERCENT. - [Recall (Verb)](): Higher is better; unit: PERCENT. - [Recall (Noun)](): Higher is better; unit: PERCENT. - [Recall (Action)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Top-5 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (Verb) | Result date | Report paper | | --- | --- | --- | --- | | Temporal Aggregate Representations | 66.7 | Not recorded | 68fa680a1e209131cea19c09 | | TBN | 66.1 | Not recorded | 68fa66391e209131cea0ef0a | | \[43\] | 65.7 | Not recorded | 68fa680a1e209131cea19c09 | | TBN | 64.75 | Not recorded | 68fa66391e209131cea0ef0a | | Temporal Aggregate Representations | 63.2 | Not recorded | 68fa680a1e209131cea19c09 | | LFB | 60 | Not recorded | 68fa680a1e209131cea19c09 | | LSTA | 59.55 | Not recorded | 68fa65a51e209131cea0b95c | | LSTA | 58.25 | Not recorded | 68fa65a51e209131cea0b95c | | RU | 56.9 | Not recorded | 68fa680a1e209131cea19c09 | | TSN w. Audio | 55.49 | Not recorded | 68fa66391e209131cea0ef0a | | TSN | 48.23 | Not recorded | 68fa65a51e209131cea0b95c | | \[8\] (from leaderboard) | 48.23 | Not recorded | 68fa66391e209131cea0ef0a | | TSN | 48.2 | Not recorded | 68fa680a1e209131cea19c09 | | TSN | 45.68 | Not recorded | 68fa65a51e209131cea0b95c | | 2SCNN | 42.16 | Not recorded | 68fa65a51e209131cea0b95c | | 2SCNN | 40.44 | Not recorded | 68fa65a51e209131cea0b95c | | Attention Clusters | 40.39 | Not recorded | 68fa66391e209131cea0ef0a | ### Temporal Aggregate Representations Top-1 Accuracy (Verb): 66.7. Result ID: 698d55708b517eb43320b77c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Auxiliary Task":"Verb + Noun classification"}. This record does not assert independent reproduction. ### TBN Top-1 Accuracy (Verb): 66.1. Result ID: 698ce2788b517eb4331d69f0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Ensemble"}. This record does not assert independent reproduction. ### \[43\] Top-1 Accuracy (Verb): 65.7. Result ID: 698d55708b517eb43320b77a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TBN Top-1 Accuracy (Verb): 64.75. Result ID: 698ce2788b517eb4331d69ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Single Model"}. This record does not assert independent reproduction. ### Temporal Aggregate Representations Top-1 Accuracy (Verb): 63.2. Result ID: 698d55708b517eb43320b77b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Auxiliary Task":"None"}. This record does not assert independent reproduction. ### LFB Top-1 Accuracy (Verb): 60. Result ID: 698d55708b517eb43320b779. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LSTA Top-1 Accuracy (Verb): 59.55. Result ID: 698cbf7c8b517eb4331c7986. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"two stream"}. This record does not assert independent reproduction. ### LSTA Top-1 Accuracy (Verb): 58.25. Result ID: 698cbf7c8b517eb4331c7985. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"RGB"}. This record does not assert independent reproduction. ### RU Top-1 Accuracy (Verb): 56.9. Result ID: 698d55708b517eb43320b778. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TSN w. Audio Top-1 Accuracy (Verb): 55.49. Result ID: 698ce2788b517eb4331d69ee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"TSN","Modality":"w. Audio"}. This record does not assert independent reproduction. ### TSN Top-1 Accuracy (Verb): 48.23. Result ID: 698cbf7c8b517eb4331c7984. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"two stream"}. This record does not assert independent reproduction. ### \[8\] (from leaderboard) Top-1 Accuracy (Verb): 48.23. Result ID: 698ce2788b517eb4331d69ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Source":"leaderboard"}. This record does not assert independent reproduction. ### TSN Top-1 Accuracy (Verb): 48.2. Result ID: 698d55708b517eb43320b777. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TSN Top-1 Accuracy (Verb): 45.68. Result ID: 698cbf7c8b517eb4331c7983. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"RGB"}. This record does not assert independent reproduction. ### 2SCNN Top-1 Accuracy (Verb): 42.16. Result ID: 698cbf7c8b517eb4331c7982. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"two stream"}. This record does not assert independent reproduction. ### 2SCNN Top-1 Accuracy (Verb): 40.44. Result ID: 698cbf7c8b517eb4331c7981. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"RGB"}. This record does not assert independent reproduction. ### Attention Clusters Top-1 Accuracy (Verb): 40.39. Result ID: 698ce2788b517eb4331d69ec. [Reporting paper]() [Method origin paper]() 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.