Structured Prediction Helps 3D Human Motion Modelling
| Autor: | Manuel Kaufmann, Otmar Hilliges, Emre Aksan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Hierarchy (mathematics) Artificial neural network Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 020207 software engineering 02 engineering and technology Kinematics computer.software_genre Motion (physics) Task (computing) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Data mining Artificial intelligence Layer (object-oriented design) Structured prediction Representation (mathematics) business computer |
| Zdroj: | 17th International Conference on Computer Vision (ICCV 2019) 2019 IEEE/CVF International Conference on Computer Vision (ICCV) ICCV |
| DOI: | 10.48550/arxiv.1910.09070 |
| Popis: | Human motion prediction is a challenging and important task in many computer vision application domains. Existing work only implicitly models the spatial structure of the human skeleton. In this paper, we propose a novel approach that decomposes the prediction into individual joints by means of a structured prediction layer that explicitly models the joint dependencies. This is implemented via a hierarchy of small-sized neural networks connected analogously to the kinematic chains in the human body as well as a joint-wise decomposition in the loss function. The proposed layer is agnostic to the underlying network and can be used with existing architectures for motion modelling. Prior work typically leverages the H3.6M dataset. We show that some state-of-the-art techniques do not perform well when trained and tested on AMASS, a recently released dataset 14 times the size of H3.6M. Our experiments indicate that the proposed layer increases the performance of motion forecasting irrespective of the base network, joint-angle representation, and prediction horizon. We furthermore show that the layer also improves motion predictions qualitatively. We make code and models publicly available at https://ait.ethz.ch/projects/2019/spl. Comment: ICCV 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|