# Action Recognition on Ego-Exo4D Cooking (test) Source: [Action Recognition on Ego-Exo4D Cooking (test)]() Collection index: [llms.txt]() Data updated: 2026-05-25T07:39:08.218Z Evaluation of Action Recognition performance on the test split of the Ego-Exo4D Cooking dataset, reporting Top-1 accuracy and Delta metrics. 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) | Ego-Exo4D Cooking (test) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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](): Higher is better; unit: PERCENT. - [Delta](): Higher is better; unit: SCALAR. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | TIME + VideoMAEv2 | 55.74 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | TIME + V-JEPA 2 | 48.52 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | TIME + CLIP | 43.27 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | TIME + DINOv3 | 43.27 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | VideoMAEv2 | 42.96 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | TIME + RVM | 39.66 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | V-JEPA 2 | 34.56 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | CLIP | 25.99 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | DINOv3 | 25.26 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | RVM | 25.1 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | | TIME | 17.13 | Not recorded | 6a13d78a6f71c5ae7dc9e8b5 | ### TIME + VideoMAEv2 Top-1 Accuracy: 55.74. Result ID: 6a13fc89fbc373592c0adb6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"TIME + VideoMAEv2","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### TIME + V-JEPA 2 Top-1 Accuracy: 48.52. Result ID: 6a13fc89fbc373592c0adb70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"TIME + V-JEPA 2","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### TIME + CLIP Top-1 Accuracy: 43.27. Result ID: 6a13fc89fbc373592c0adb6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"TIME + CLIP (4f)","Number of frames":"4f","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### TIME + DINOv3 Top-1 Accuracy: 43.27. Result ID: 6a13fc89fbc373592c0adb6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"TIME + DINOv3 (4f)","Number of frames":"4f","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### VideoMAEv2 Top-1 Accuracy: 42.96. Result ID: 6a13fc89fbc373592c0adb6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"VideoMAEv2","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### TIME + RVM Top-1 Accuracy: 39.66. Result ID: 6a13fc89fbc373592c0adb6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"TIME + RVM","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### V-JEPA 2 Top-1 Accuracy: 34.56. Result ID: 6a13fc89fbc373592c0adb6b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Strategy":"V-JEPA 2","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### CLIP Top-1 Accuracy: 25.99. Result ID: 6a13fc89fbc373592c0adb66. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Strategy":"CLIP (4f)","Number of frames":"4f","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### DINOv3 Top-1 Accuracy: 25.26. Result ID: 6a13fc89fbc373592c0adb67. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Strategy":"DINOv3 (4f)","Number of frames":"4f","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### RVM Top-1 Accuracy: 25.1. Result ID: 6a13fc89fbc373592c0adb69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"RVM","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. ### TIME Top-1 Accuracy: 17.13. Result ID: 6a13fc89fbc373592c0adb68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Strategy":"TIME (Ours)","Evaluation Protocol":"Video Probing"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.