ARCH
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Utterance-level classification | ARCH (RAVDESS, EMOVO, AudioMNIST, SLURP) post-VQ 57 | RAVDESS Accuracy37.85 | 15 | |
| Semantic Representation Evaluation | ARCH (test) | RAVDESS48.96 | 13 | |
| Pseudotime estimation | Arch | Spearman Correlation0.99 | 10 | |
| Continuous-time dynamics estimation | Arch synthetic | LDTW3.85 | 10 | |
| Semantic Representation Classification | ARCH Reconstruction Domain | RAVDESS Accuracy81.25 | 10 | |
| Speech Classification | ARCH | RAVDESS Score37.5 | 8 | |
| Image-to-Text Cross-modal Retrieval | ARCH (test) | R@11,256 | 8 | |
| Text-to-Image Cross-modal Retrieval | ARCH (test) | R@111.17 | 8 | |
| Image-to-Text Retrieval | ARCH | R@19.97 | 7 | |
| Text-to-Image Retrieval | ARCH | R@18.89 | 7 | |
| Surface Reconstruction | Arch-100 (test) | Mean Hausdorff Error (MHE)1.066 | 6 |
Showing 11 of 11 rows