File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/2820903.2820918
- Scopus: eid_2-s2.0-84960436158
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Learning motion manifolds with convolutional autoencoders
Title | Learning motion manifolds with convolutional autoencoders |
---|---|
Authors | |
Keywords | Motion data Convolutional neural networks Animation Character animation Deep neural networks Manifold learning Machine learning Autoencoding |
Issue Date | 2015 |
Citation | SIGGRAPH Asia 2015 Technical Briefs, SA 2015, 2015, article no. 18 How to Cite? |
Abstract | © 2015 ACM. We present a technique for learning a manifold of human motion data using Convolutional Autoencoders. Our approach is capable of learning a manifold on the complete CMU database of human motion. This manifold can be treated as a prior probability distribution over human motion data, which has many applications in animation research, including projecting invalid or corrupt motion onto the manifold for removing error, computing similarity between motions using geodesic distance along the manifold, and interpolation of motion along the manifold for avoiding blending artefacts. |
Persistent Identifier | http://hdl.handle.net/10722/288691 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Holden, Daniel | - |
dc.contributor.author | Saito, Jun | - |
dc.contributor.author | Komura, Taku | - |
dc.contributor.author | Joyce, Thomas | - |
dc.date.accessioned | 2020-10-12T08:05:37Z | - |
dc.date.available | 2020-10-12T08:05:37Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | SIGGRAPH Asia 2015 Technical Briefs, SA 2015, 2015, article no. 18 | - |
dc.identifier.uri | http://hdl.handle.net/10722/288691 | - |
dc.description.abstract | © 2015 ACM. We present a technique for learning a manifold of human motion data using Convolutional Autoencoders. Our approach is capable of learning a manifold on the complete CMU database of human motion. This manifold can be treated as a prior probability distribution over human motion data, which has many applications in animation research, including projecting invalid or corrupt motion onto the manifold for removing error, computing similarity between motions using geodesic distance along the manifold, and interpolation of motion along the manifold for avoiding blending artefacts. | - |
dc.language | eng | - |
dc.relation.ispartof | SIGGRAPH Asia 2015 Technical Briefs, SA 2015 | - |
dc.subject | Motion data | - |
dc.subject | Convolutional neural networks | - |
dc.subject | Animation | - |
dc.subject | Character animation | - |
dc.subject | Deep neural networks | - |
dc.subject | Manifold learning | - |
dc.subject | Machine learning | - |
dc.subject | Autoencoding | - |
dc.title | Learning motion manifolds with convolutional autoencoders | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/2820903.2820918 | - |
dc.identifier.scopus | eid_2-s2.0-84960436158 | - |
dc.identifier.spage | article no. 18 | - |
dc.identifier.epage | article no. 18 | - |