GENERATIVE MODEL-ENHANCED HUMAN MOTION PREDICTION

Anthony Bourached, Ryan-Rhys Griffiths, Robert Gray, Ashwani Jha, Parashkev Nachev

Abstract: The task of predicting human motion is complicated by the natural heterogeneity and compositionality of actions, necessitating robustness to distributional shifts as far as out-of-distribution (OoD). Here we formulate a new OoD benchmark based on the Human3.6M and CMU motion capture datasets, and introduce a hy- brid framework for hardening discriminative architectures to OoD failure by aug- menting them with a generative model. When applied to current state-of-the-art discriminative models, we show that the proposed approach improves OoD ro- bustness without sacrificing in-distribution performance, and can theoretically facilitate model interpretability. We suggest human motion predictors ought to be constructed with OoD challenges in mind, and provide an extensible general framework for hard- ening diverse discriminative architectures to extreme distributional shift.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2010.11699/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=HF33Ewoz_Y