Learning to Generate Long-term Future via Hierarchical Prediction
ثبت نشده
چکیده
In this section, we evaluate the predictions by deciles of motion similar to Villegas et al. (2017) using Peak Signal-to-Noise Ratio (PSNR) measure, where the 10th decile contains videos with the most overall motion. We add a modification to our hierarchical method based on a simple heuristic by which we copy the background pixels from the last observed frame using the predicted pose heat-maps as foreground/background masks (Ours BG). Additionally, we perform experiments based on an oracle that provides our image generator the exact future pose trajectories (Ours GT-pose⇤) and we also apply the previously mentioned heuristics (Ours GT-pose BG⇤). We put * marks to clarify that these are hypothetical methods as they require ground-truth future pose trajectories.
منابع مشابه
Simulation of Long-term Returns with Stochastic Correlations
This paper focuses on a nonlinear stochastic model for financial simulation and forecasting based on assumptions of multivariate stochastic correlation, with an application to the European market. We present in particular the key elements of a structured hierarchical econometric model that can be used to forecast financial and commodity markets relying on statistical and simulation methods. The...
متن کاملLearning to Generate Long-term Future via Hierarchical Prediction
We propose a hierarchical approach for making long-term predictions of future frames. To avoid inherent compounding errors in recursive pixellevel prediction, we propose to first estimate highlevel 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 fu...
متن کاملSequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture
In this paper, we propose a deep learning-based vehicle trajectory prediction technique which can generate the future trajectory sequence of the surrounding vehicles in real time. We employ the encoder-decoder architecture which analyzes the pattern underlying in the past trajectory using the long short term memory (LSTM)-based encoder and generates the future trajectory sequence using the LSTM...
متن کاملHybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data
Time series data constitutes a distinct and growing problem in machine learning. As the corpus of time series data grows larger, deep models that simultaneously learn features and classify with these features can be intractable or suboptimal. In this paper, we present feature learning via long short term memory (LSTM) networks and prediction via gradient boosting trees (XGB). Focusing on the co...
متن کاملHierarchical Model for Long-term Video Prediction
Video prediction has been an active topic of research in the past few years. Many algorithms focus on pixel-level predictions, which generates results that blur and disintegrate within a few frames. In this project, we use a hierarchical approach for long-term video prediction. We aim at estimating high-level structure in the input frame first, then predict how that structure grows in the futur...
متن کامل