Time Series Classification On Auslan
评估指标
Accuracy
NLL
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Accuracy | NLL | Paper Title | Repository |
|---|---|---|---|---|
| GP-Sig-GRU | 0.978 | 0.123 | Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances | - |
| FCN-SNLST | 0.993 | - | Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections | - |
| GP-KConv1D | 0.784 | 1.900 | Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances | - |
| MALSTM-FCN | 0.96 | - | Multivariate LSTM-FCNs for Time Series Classification | - |
| GP-Sig | 0.925 | 0.550 | Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances | - |
| SNLST | 0.969 | - | Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections | - |
| GP-LSTM | 0.880 | 0.650 | Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances | - |
| GP-Sig-LSTM | 0.983 | 0.106 | Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances | - |
| GP-GRU | 0.949 | 0.248 | Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances | - |
0 of 9 row(s) selected.