# Speaking Target Identification on YouTube v1.0 (test) Source: [Speaking Target Identification on YouTube v1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:38.167Z Evaluation of Speaking Target Identification performance on the test split of the YouTube v1.0 dataset, measured using Accuracy. 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 | Speaking Target Identification | | Dataset (including any stated split) | YouTube v1.0 (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | RoBERTa-based Our Baseline | 74.5 | Not recorded | 68fa73101e209131cea5a3aa | | RoBERTa + MVIT | 73.1 | Not recorded | 68fa73101e209131cea5a3aa | | BERT-based Our Baseline | 72.7 | Not recorded | 68fa73101e209131cea5a3aa | | RoBERTa + DINOv2 | 72.7 | Not recorded | 68fa73101e209131cea5a3aa | | RoBERTa | 72.4 | Not recorded | 68fa73101e209131cea5a3aa | | ELECTRA-based Our Baseline | 69.6 | Not recorded | 68fa73101e209131cea5a3aa | | BERT + MVIT | 66.9 | Not recorded | 68fa73101e209131cea5a3aa | | BERT + DINOv2 | 66.4 | Not recorded | 68fa73101e209131cea5a3aa | | BERT | 65.8 | Not recorded | 68fa73101e209131cea5a3aa | | ELECTRA | 65.8 | Not recorded | 68fa73101e209131cea5a3aa | | ELECTRA + DINOv2 | 65.3 | Not recorded | 68fa73101e209131cea5a3aa | | ELECTRA + MVIT | 64.6 | Not recorded | 68fa73101e209131cea5a3aa | ### RoBERTa-based Our Baseline Accuracy: 74.5. Result ID: 6992a95a3a6c3148491083c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":true}. This record does not assert independent reproduction. ### RoBERTa + MVIT Accuracy: 73.1. Result ID: 6992a95a3a6c3148491083c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":false}. This record does not assert independent reproduction. ### BERT-based Our Baseline Accuracy: 72.7. Result ID: 6992a95a3a6c3148491083bd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":true}. This record does not assert independent reproduction. ### RoBERTa + DINOv2 Accuracy: 72.7. Result ID: 6992a95a3a6c3148491083bf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":false}. This record does not assert independent reproduction. ### RoBERTa Accuracy: 72.4. Result ID: 6992a95a3a6c3148491083be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ELECTRA-based Our Baseline Accuracy: 69.6. Result ID: 6992a95a3a6c3148491083c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":true}. This record does not assert independent reproduction. ### BERT + MVIT Accuracy: 66.9. Result ID: 6992a95a3a6c3148491083bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":false}. This record does not assert independent reproduction. ### BERT + DINOv2 Accuracy: 66.4. Result ID: 6992a95a3a6c3148491083bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":false}. This record does not assert independent reproduction. ### BERT Accuracy: 65.8. Result ID: 6992a95a3a6c3148491083ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ELECTRA Accuracy: 65.8. Result ID: 6992a95a3a6c3148491083c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ELECTRA + DINOv2 Accuracy: 65.3. Result ID: 6992a95a3a6c3148491083c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":false}. This record does not assert independent reproduction. ### ELECTRA + MVIT Accuracy: 64.6. Result ID: 6992a95a3a6c3148491083c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Densely Aligned":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.