Extracting variation and spatiotemporal features via limited frames remains as an unsolved and challenging problem in video prediction. Inherent uncertainty among consecutive frames exacerbates the difficulty in long-term prediction. To tackle the problem, we focus on capturing context correlations and multi-scale spatiotemporal flows, then propose CMS-LSTM by integrating two effective and lightweight blocks, namely Context-Embedding (CE) and Spatiotemporal-Expression (SE) block, into ConvLSTM backbone. CE block is designed for abundant context interactions, while SE block focuses on multi-scale spatiotemporal expression in hidden states. The newly introduced blocks also facilitate other spatiotemporal models (e.g., PredRNN, SA-ConvLSTM) to produce representative implicit features for video prediction. Qualitative and quantitative experiments demonstrate the effectiveness and flexibility of our proposed method. We use fewer parameters to reach markedly state-of-the-art results on Moving MNIST and TaxiBJ datasets in numbers of metrics. All source code is available at https://github.com/czh-98/CMS-LSTM.
تحميل البحث