Research Article
[Retracted] The Effectiveness of Pictorial Aesthetics Based on Multiview Parallel Neural Networks in Art-Oriented Teaching
Table 3
Performance comparison between MVPD-CNN and baseline under different view inputs.
| | Method | Rp/Sig | MSE |
| | AVA [16] | 0.462/0.000 | 0.532 | | Zhang and Chen [23] | 0.556/0.000 | 0.446 | | RAPID [13] | 0.645/0.000 | 0.371 | | DMA-Net [25] | 0.654/0.000 | 0.352 | | MSDLM [28] | 0.669/0.000 | 0.344 | | SCNN-Arc3 | 0.712/0.000 | 0.285 | | MVPD-CNN-global | 0.731/0.000 | 0.267 | | MVPD-CNN-global | 0.782/0.000 | 0.212 | | MVPD-CNN-hybrid | 0.791/0.000 | 0.193 |
|
|
