Multi-level Motion Attention for Human Motion Prediction

dc.contributor.authorMao, Wei
dc.contributor.authorLiu, Miaomiao
dc.contributor.authorSalzmann, Mathieu
dc.contributor.authorLi, Hongdong
dc.date.accessioned2023-12-08T00:21:00Z
dc.date.issued2021
dc.date.updated2022-09-04T08:16:51Z
dc.description.abstractHuman motion prediction aims to forecast future human poses given a historical motion. Whether based on recurrent or feed-forward neural networks, existing learning based methods fail to model the observation that human motion tends to repeat itself, even for complex sports actions and cooking activities. Here, we introduce an attention based feed-forward network that explicitly leverages this observation. In particular, instead of modeling frame-wise attention via pose similarity, we propose to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences. In this context, we study the use of different types of attention, computed at joint, body part, and full pose levels. Aggregating the relevant past motions and processing the result with a graph convolutional network allows us to effectively exploit motion patterns from the long-term history to predict the future poses. Our experiments on Human3.6M, AMASS and 3DPW validate the benefits of our approach for both periodical and non-periodical actions. Thanks to our attention model, it yields state-of-the-art results on all three datasets. Our code is available at https://github.com/wei-mao-2019/HisRepItself.en_AU
dc.description.sponsorshipThis research was supported in part by the Australia Research Council DECRA Fellowship (DE180100628) and ARC Discovery Grant (DP200102274).en_AU
dc.format.mimetypeapplication/pdfen_AU
dc.identifier.issn0920-5691en_AU
dc.identifier.urihttp://hdl.handle.net/1885/307738
dc.language.isoen_AUen_AU
dc.publisherSpringeren_AU
dc.relationhttp://purl.org/au-research/grants/arc/DE180100628en_AU
dc.relationhttp://purl.org/au-research/grants/arc/DP200102274en_AU
dc.rights© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021en_AU
dc.sourceInternational Journal of Computer Visionen_AU
dc.subjectHuman motion predictionen_AU
dc.subjectMotion attentionen_AU
dc.subjectDeep learningen_AU
dc.titleMulti-level Motion Attention for Human Motion Predictionen_AU
dc.typeJournal articleen_AU
local.bibliographicCitation.lastpage2535en_AU
local.bibliographicCitation.startpage2513en_AU
local.contributor.affiliationLiu, Miaomiao, College of Engineering and Computer Science, ANUen_AU
local.contributor.affiliationSalzmann, Mathieu, EPFLen_AU
local.contributor.affiliationLi, Hongdong, College of Engineering and Computer Science, ANUen_AU
local.contributor.affiliationMao, Wei, College of Engineering and Computer Science, ANUen_AU
local.contributor.authoremailu5266426@anu.edu.auen_AU
local.contributor.authoruidLiu, Miaomiao, u5266426en_AU
local.contributor.authoruidLi, Hongdong, u4056952en_AU
local.contributor.authoruidMao, Wei, u5914243en_AU
local.description.embargo2099-12-31
local.description.notesImported from ARIESen_AU
local.identifier.absfor461104 - Neural networksen_AU
local.identifier.absfor460304 - Computer visionen_AU
local.identifier.ariespublicationa383154xPUB20105en_AU
local.identifier.citationvolume129en_AU
local.identifier.doi10.1007/s11263-021-01483-7en_AU
local.identifier.scopusID2-s2.0-85108155323
local.identifier.thomsonIDWOS:000662108800001
local.identifier.uidSubmittedBya383154en_AU
local.publisher.urlhttps://link.springer.com/en_AU
local.type.statusPublished Versionen_AU

Downloads

Back to topicon-arrow-up-solid
 
APRU
IARU
 
edX
Group of Eight Member

Acknowledgement of Country

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.


Contact ANUCopyrightDisclaimerPrivacyFreedom of Information

+61 2 6125 5111 The Australian National University, Canberra

TEQSA Provider ID: PRV12002 (Australian University) CRICOS Provider Code: 00120C ABN: 52 234 063 906