Data to 7 Oct 2026

PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning

arXiv 1804.06300 ↗First posted 17 Apr 2018cs.LG cs.CV stat.MLcited by 122

Not on the map. Why?

Abstract (arXiv)

We present PredRNN++, an improved recurrent network for video predictive learning. In pursuit of a greater spatiotemporal modeling capability, our approach increases the transition depth between adjacent states by leveraging a novel recurrent unit, which is named Causal LSTM for re-organizing the spatial and temporal memories in a cascaded mechanism. However, there is still a dilemma in video predictive learning: increasingly deep-in-time models have been designed for capturing complex variations, while introducing more difficulties in the gradient back-propagation. To alleviate this undesirable effect, we propose a Gradient Highway architecture, which provides alternative shorter routes for gradient flows from outputs back to long-range inputs. This architecture works seamlessly with causal LSTMs, enabling PredRNN++ to capture short-term and long-term dependencies adaptively. We assess our model on both synthetic and real video datasets, showing its ability to ease the vanishing gradient problem and yield state-of-the-art prediction results even in a difficult objects occlusion scenario.

Key facts. Cited by 122 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 27; 2023: 20; 2024: 23; 2025: 16; 2026: 22.

122 papers.

Sort:

By area:

2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 181
2022SimVP: Simpler yet Better Video Predictioncited by 181
2022Latency-Aware Collaborative Perceptioncited by 86
2022Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learningcited by 84
2021Video Prediction Recalling Long-term Motion Context via Memory Alignment Learningcited by 62
2022Efficient Video Prediction via Sparsely Conditioned Flow Matchingcited by 54
2023OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learningcited by 53
2023DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videoscited by 42
2024VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecastingcited by 35
2023SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTMcited by 32
2022STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Predictioncited by 31
2022SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbationcited by 31

38 more

2022SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learningcited by 20
2023MMVP: Motion-Matrix-based Video Predictioncited by 18
2022VPTR: Efficient Transformers for Video Predictioncited by 17
2022Dynamics-Aware Spatiotemporal Occupancy Prediction in Urban Environmentscited by 17
2022MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Predictioncited by 17
2024Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcastingcited by 16
2025Deep Learning and Foundation Models for Weather Prediction: A Surveycited by 15
2022Advancing Learned Video Compression with In-loop Frame Predictioncited by 14
2023Implicit Stacked Autoregressive Model for Video Predictioncited by 14
2022Video Prediction by Efficient Transformerscited by 12
2023TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regressioncited by 12
2024Diffusion Transformers as Open-World Spatiotemporal Foundation Modelscited by 10
2021Local Frequency Domain Transformer Networks for Video Predictioncited by 9
2021Learning Scene Dynamics from Point Cloud Sequencescited by 9
2023Deterministic Guidance Diffusion Model for Probabilistic Weather Forecastingcited by 9
2024GPTCast: a weather language model for precipitation nowcastingcited by 8
2021Physics-informed generative neural network: an application to troposphere temperature predictioncited by 7
2021Learning to Transfer for Traffic Forecasting via Multi-task Learningcited by 7
2022A unified model for continuous conditional video predictioncited by 7
2023Triplet Attention Transformer for Spatiotemporal Predictive Learningcited by 7
2024DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecastingcited by 7
2024UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Predictioncited by 7
2022Data-Driven Short-Term Daily Operational Sea Ice Regional Forecastingcited by 6
2024PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplinescited by 6
2024Video Prediction Transformers without Recurrence or Convolutioncited by 6
2022MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learningcited by 5
2022A Novel Transformer Network with Shifted Window Cross-Attention for Spatiotemporal Weather Forecastingcited by 5
2022WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Predictioncited by 5
2023S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Predictioncited by 5
2024Learning Locally Interacting Discrete Dynamical Systems: Towards Data-Efficient and Scalable Predictioncited by 5
2024Advection Augmented Convolutional Neural Networkscited by 5
2021CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learningcited by 4
2023MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domaincited by 4
2024Motion Graph Unleashed: A Novel Approach to Video Predictioncited by 4
2024Video RWKV:Video Action Recognition Based RWKVcited by 4
2023Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approachcited by 3
2025UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplinescited by 3
2021RAP-Net: Region Attention Predictive Network for Precipitation Nowcastingcited by 2

50 most cited of 122 All 122 (JSON)