AI RESEARCH
CNN-based Multi-In-Multi-Out Model for Efficient Spatiotemporal Prediction
arXiv CS.CV
•
ArXi:2605.01277v1 Announce Type: new Recently, Convolutional Neural Network (CNN) or Transformer architecture based models have been proposed to overcome the limitations of Recurrent Neural Network (RNN) based models in spatiotemporal prediction. These models prevent the inefficiency of parallelization limitation due to the sequential properties and stacked error due to the recursive method, and show high performance. Novertheless, there are still some challengies.