Journal article Open Access

Deep Motifs and Motion Signatures

Aristidou Andreas; Cohen-Or Daniel; Hodgins Jessica K; Chrysanthou Yiorgos; Shamir Ariel

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 are both common and descriptive, and their distribution represents the motion sequence. To cluster words and find motifs, the challenge is to define an effective feature space, where the distances among motion words are semantically meaningful, and where variations in speed and duration are handled. To this end, we use a deep neural network to embed the motion words into feature space using a triplet loss function. To define a signature, we choose a finite set of motion-motifs, creating a bag-of-motifs representation for the sequence. Motion signatures are agnostic to movement order, speed or duration variations, and can distinguish fine-grained differences between motions of the same class. We illustrate examples of characterizing motion sequences by motifs, and for the use of motion signatures in anumber of applications.

This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2)  and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.  @2018 ACM Copyright under the CC-BY-NC-ND 4.0 license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Citation: Andreas Aristidou, Daniel Cohen-Or, Jessica K. Hodgins, Yiorgos Chrysanthou, and Ariel Shamir. 2018. Deep motifs and motion signatures. ACM Trans. Graph. 37, 6, Article 187 (December 2018), 13 pages. DOI: https://doi.org/10.1145/3272127.3275038
Files (25.3 MB)
Name Size
DeepSignatures.pdf
md5:e4716169f486e6ad90f0633c6d8564df
25.3 MB Download
59
33
views
downloads
Views 59
Downloads 33
Data volume 835.0 MB
Unique views 46
Unique downloads 32

Share

Cite as