Human Pose Forecasting via Deep Markov Models
This work addresses human pose forecasting for applications like human-robot interaction and autonomous driving, but it appears incremental as it builds on existing methods with a new evaluation metric and dataset.
The paper tackles the problem of long-range human pose forecasting by proposing a generative framework using variational autoencoders based on Deep Markov Models, and it demonstrates promising results on the new Ikea FA dataset and the existing NTU RGB+D dataset.
Human pose forecasting is an important problem in computer vision with applications to human-robot interaction, visual surveillance, and autonomous driving. Usually, forecasting algorithms use 3D skeleton sequences and are trained to forecast for a few milliseconds into the future. Long-range forecasting is challenging due to the difficulty of estimating how long a person continues an activity. To this end, our contributions are threefold: (i) we propose a generative framework for poses using variational autoencoders based on Deep Markov Models (DMMs); (ii) we evaluate our pose forecasts using a pose-based action classifier, which we argue better reflects the subjective quality of pose forecasts than distance in coordinate space; (iii) last, for evaluation of the new model, we introduce a 480,000-frame video dataset called Ikea Furniture Assembly (Ikea FA), which depicts humans repeatedly assembling and disassembling furniture. We demonstrate promising results for our approach on both Ikea FA and the existing NTU RGB+D dataset.