# Action Recognition on LT-NTU IF = 100 60 (cross-subject) Source: [Action Recognition on LT-NTU IF = 100 60 (cross-subject)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:15.886Z Evaluation of video action recognition performance on the LT-NTU IF=100 60 dataset using the cross-subject protocol, reporting accuracy stratified by sample size (Many, Medium, Few). 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) | LT-NTU IF = 100 60 (cross-subject) | | Metric | Top-1 Accuracy (Overall) | | 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 - [Top-1 Accuracy (Overall)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Many Samples)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Medium Samples)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Few Samples)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (Overall) | Result date | Report paper | | --- | --- | --- | --- | | Shap-Mix | 80.8 | Not recorded | 68fa74231e209131cea5fe66 | | GLMC | 78.8 | Not recorded | 68fa74231e209131cea5fe66 | | Remix-DRW | 78.7 | Not recorded | 68fa74231e209131cea5fe66 | | Focal Loss | 77.6 | Not recorded | 68fa74231e209131cea5fe66 | | Balanced Softmax (BS) | 77.6 | Not recorded | 68fa74231e209131cea5fe66 | | BS+Max Norm | 77.5 | Not recorded | 68fa74231e209131cea5fe66 | | BCL | 77.3 | Not recorded | 68fa74231e209131cea5fe66 | | BRL | 76.9 | Not recorded | 68fa74231e209131cea5fe66 | | FSA | 76.8 | Not recorded | 68fa74231e209131cea5fe66 | | PaCo | 76.6 | Not recorded | 68fa74231e209131cea5fe66 | | RIDE (3 experts) | 76.6 | Not recorded | 68fa74231e209131cea5fe66 | | LDAM-DRW | 76.4 | Not recorded | 68fa74231e209131cea5fe66 | | IB Loss | 76 | Not recorded | 68fa74231e209131cea5fe66 | | Mixup | 75.9 | Not recorded | 68fa74231e209131cea5fe66 | | ROS | 74.8 | Not recorded | 68fa74231e209131cea5fe66 | | Cross-Entropy Loss | 74.4 | Not recorded | 68fa74231e209131cea5fe66 | | CB Loss | 72.4 | Not recorded | 68fa74231e209131cea5fe66 | ### Shap-Mix Top-1 Accuracy (Overall): 80.8. Result ID: 6993205e3a6c31484913e6ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Augmentation","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### GLMC Top-1 Accuracy (Overall): 78.8. Result ID: 6993205e3a6c31484913e6a1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Augmentation","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### Remix-DRW Top-1 Accuracy (Overall): 78.7. Result ID: 6993205e3a6c31484913e69f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Augmentation","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### Focal Loss Top-1 Accuracy (Overall): 77.6. Result ID: 6993205e3a6c31484913e6a4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Reweighting & Resampling","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### Balanced Softmax (BS) Top-1 Accuracy (Overall): 77.6. Result ID: 6993205e3a6c31484913e6a7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Reweighting & Resampling","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### BS+Max Norm Top-1 Accuracy (Overall): 77.5. Result ID: 6993205e3a6c31484913e6a9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Decoupling","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### BCL Top-1 Accuracy (Overall): 77.3. Result ID: 6993205e3a6c31484913e6ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Contrastive Learning","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### BRL Top-1 Accuracy (Overall): 76.9. Result ID: 6993205e3a6c31484913e6a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Augmentation","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### FSA Top-1 Accuracy (Overall): 76.8. Result ID: 6993205e3a6c31484913e6a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Augmentation","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### PaCo Top-1 Accuracy (Overall): 76.6. Result ID: 6993205e3a6c31484913e6aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Contrastive Learning","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### RIDE (3 experts) Top-1 Accuracy (Overall): 76.6. Result ID: 6993205e3a6c31484913e6ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Ensemble","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### LDAM-DRW Top-1 Accuracy (Overall): 76.4. Result ID: 6993205e3a6c31484913e6a6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Reweighting & Resampling","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### IB Loss Top-1 Accuracy (Overall): 76. Result ID: 6993205e3a6c31484913e6a8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Reweighting & Resampling","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### Mixup Top-1 Accuracy (Overall): 75.9. Result ID: 6993205e3a6c31484913e69e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Augmentation","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### ROS Top-1 Accuracy (Overall): 74.8. Result ID: 6993205e3a6c31484913e6a3. [Reporting paper]() Recorded evaluation configuration: {"Category":"Reweighting & Resampling","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### Cross-Entropy Loss Top-1 Accuracy (Overall): 74.4. Result ID: 6993205e3a6c31484913e69d. [Reporting paper]() Recorded evaluation configuration: {"Category":"-","Input Stream":"Single Joint"}. This record does not assert independent reproduction. ### CB Loss Top-1 Accuracy (Overall): 72.4. Result ID: 6993205e3a6c31484913e6a5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Reweighting & Resampling","Input Stream":"Single Joint"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.