publication . Article . 2019

Deep motifs and motion signatures

Andreas Aristidou; Daniel Cohen-Or; Jessica K. Hodgins; Yiorgos Chrysanthou; Ariel Shamir;
Open Access
  • Published: 10 Jan 2019
  • Publisher: Association for Computing Machinery (ACM)
Abstract
Many analysis tasks for human motion rely on high-level similarity between sequences of motions, that are not an exact matches in joint angles, timing, or ordering of actions. Even the same movements performed by the same person can vary in duration and speed. Similar motions are characterized by similar sets of actions that appear frequently. In this paper we introduce motion motifs and motion signatures that are a succinct but descriptive representation of motion sequences. We first break the motion sequences to short-term movements called motion words, and then cluster the words in a high-dimensional feature space to find motifs. Hence, motifs are words that ...
Persistent Identifiers
Subjects
free text keywords: Motion capture, Motion processing, Animation, Motion Word, Motif, Motion Signature, Convolutional Network,, Triplet Loss, Artificial neural network, Feature vector, Human motion, Animation, Pattern recognition, Artificial intelligence, business.industry, business, Finite set, Computer science, Triplet loss
Funded by
EC| RISE
Project
RISE
Research Center on Interactive Media, Smart System and Emerging Technologies
  • Funder: European Commission (EC)
  • Project Code: 739578
  • Funding stream: H2020 | SGA-CSA
Validated by funder
Any information missing or wrong?Report an Issue