Recurrent Semi-supervised Classification and Constrained Adversarial Generation with Motion Capture Data
This work addresses motion analysis and animation generation for computer graphics or robotics, but it is incremental as it builds on existing recurrent and adversarial methods.
The paper tackles semi-supervised classification and adversarial generation for motion capture data, finding that multiple reconstruction modules improve classification with limited labeled data and that constraints stabilize training for future movement generation.
We explore recurrent encoder multi-decoder neural network architectures for semi-supervised sequence classification and reconstruction. We find that the use of multiple reconstruction modules helps models generalize in a classification task when only a small amount of labeled data is available, which is often the case in practice. Such models provide useful high-level representations of motions allowing clustering, searching and faster labeling of new sequences. We also propose a new, realistic partitioning of a well-known, high quality motion-capture dataset for better evaluations. We further explore a novel formulation for future-predicting decoders based on conditional recurrent generative adversarial networks, for which we propose both soft and hard constraints for transition generation derived from desired physical properties of synthesized future movements and desired animation goals. We find that using such constraints allow to stabilize the training of recurrent adversarial architectures for animation generation.