Modeling human motion with quaternion-based neural networks

DOI10.1007/S11263-019-01245-6zbMath1477.68407arXiv1901.07677OpenAlexW3101017148WikidataQ127129177 ScholiaQ127129177MaRDI QIDQ2193564

Michael Auli, David Grangier, Dario Pavllo, Christoph Feichtenhofer

Publication date: 20 August 2020

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.07677

zbMATH Keywords

neural networksquaterniondeep learningmotion generationhuman motion modeling

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Machine vision and scene understanding (68T45)

Related Items (4)

A direct analysis method to Lagrangian global exponential stability for quaternion memristive neural networks with mixed delays ⋮ Hyers-Ulam stability to linear nonhomogeneous quaternion-valued matrix difference equations via complex representation ⋮ A direct analysis method to state bounding for high‐order quaternion Hopfield neural networks with mixed delays and bounded disturbances ⋮ New applications of Clifford's geometric algebra

Uses Software

• ImageNet
• Adam
• AlexNet
• WaveNet
• Human3.6M
• CMU Motion Capture

Cites Work

• Unnamed Item
• Unnamed Item
• Metrics for 3D rotations: comparison and analysis
• Motion synthesis from annotations
• 10.1162/153244303322533223
• Planning Algorithms

This page was built for publication: Modeling human motion with quaternion-based neural networks