all AI news
CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learning. (arXiv:2102.03586v4 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Spatiotemporal predictive learning (ST-PL) is a hotspot with numerous
applications, such as object movement and meteorological prediction. It aims at
predicting the subsequent frames via observed sequences. However, inherent
uncertainty among consecutive frames exacerbates the difficulty in long-term
prediction. To tackle the increasing ambiguity during forecasting, we design
CMS-LSTM to focus on context correlations and multi-scale spatiotemporal flow
with details on fine-grained locals, containing two elaborate designed blocks:
Context Embedding (CE) and Spatiotemporal Expression (SE) blocks. CE is
designed for …
arxiv cms context cv embedding learning lstm predictive scale