KTH

Overview edit

Variants: KTH

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Video Prediction - Metrics: FVD, SSIM, PSNR, LPIPS, Cond, Train, Pred, Params (M), MSE, Diversity
• Action Recognition - Metrics: 16:9 Accuracy

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks (2022) -
• SLAMP: Stochastic Latent Appearance and Motion Prediction (2021) -
• Accurate Grid Keypoint Learning for Efficient Video Prediction (2021) -
• Diverse Video Generation using a Gaussian Process Trigger (2021) -
• Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning (2021) -
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning (2021) -
• Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction (2020) -
• Stochastic Latent Residual Video Prediction (2020) -
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning (2020) -
• Unsupervised Learning of Object Structure and Dynamics from Videos (2019) -
• PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning (2018) -
• Mutual Suppression Network for Video Prediction using Disentangled Features (2018) -
• Stochastic Adversarial Video Prediction (2018) -
• Stochastic Video Generation with a Learned Prior (2018) -
• Folded Recurrent Neural Networks for Future Video Prediction (2017) -
• Stochastic Variational Video Prediction (2017) -
• Decomposing Motion and Content for Natural Video Sequence Prediction (2017) -
• Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model (2017) -
• Video Pixel Networks (2016) -
• Dynamic Filter Networks (2016) -