arXiv (Cornell University) · 2017 · 180 citations · 5 references
ComputingComputer ScienceComputer VisionMachine LearningPredictive AnalyticsDeep LearningLong-term ForecastingRepresentation LearningScene UnderstandingSequence LearningVideo AnalysisConvolutional Neural NetworksEncoder-decoder ArchitecturesError PropagationFramesFuture Frame PredictionVideo GenerationVideo Representation Learning
We propose a hierarchical approach for making long-term predictions of future frames. To avoid inherent compounding errors in recursive pixel-level prediction, we propose to first estimate high-level structure in the input frames, then predict how that structure evolves in the future, and finally by observing a single frame from the past and the predicted high-level structure, we construct the future frames without having to observe any of the pixel-level predictions. Long-term video prediction is difficult to perform by recurrently observing the predicted frames because the small errors in pixel space exponentially amplify as predictions are made deeper into the future. Our approach prevents pixel-level error propagation from happening by removing the need to observe the predicted frames. Our model is built with a combination of LSTM and analogy based encoder-decoder convolutional neural networks, which independently predict the video structure and generate the future frames, respectively. In experiments, our model is evaluated on the Human3.6M and Penn Action datasets on the task of long-term pixel-level video prediction of humans performing actions and demonstrate significantly better results than the state-of-the-art.
5
Stacked Hourglass Networks for Human Pose Estimation
Alejandro Newell, Kaiyu Yang, Jia Deng · arXiv (Cornell University) · 2016 · 541 citations · Full text
Recurrent Network Models for Human Dynamics
Katerina Fragkiadaki, Sergey Levine, Panna Felsen et al. · arXiv (Cornell University) · 2015 · 73 citations · Full text
Forecasting Human Dynamics from Static Images
Yu-Wei Chao, Brian Price, Scott Cohen et al. · arXiv (Cornell University) · 2017 · 14 citations · Full text