File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-319-46487-9_50
- Scopus: eid_2-s2.0-84990059379
- WOS: WOS:000389384800050
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Spatio-temporal LSTM with trust gates for 3D human action recognition
Title | Spatio-temporal LSTM with trust gates for 3D human action recognition |
---|---|
Authors | |
Keywords | 3D action recognition Long short-term memory Recurrent neural networks Spatio-temporal analysis Trust gate |
Issue Date | 2016 |
Publisher | Springer |
Citation | 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 11-14 October 2016. In Leibe, B, Matas, J, Sebe, N, et al. (Eds.), Computer Vision - ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III, p. 816-833. Cham: Springer, 2016 How to Cite? |
Abstract | 3D action recognition–analysis of human actions based on 3D skeleton data–becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based learning methods to model the contextual dependency in the temporal domain. In this paper, we extend this idea to spatio-temporal domains to analyze the hidden sources of action-related information within the input data over both domains concurrently. Inspired by the graphical structure of the human skeleton, we further propose a more powerful tree-structure based traversal method. To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell. Our method achieves state-of-the-art performance on 4 challenging benchmark datasets for 3D human action analysis. |
Persistent Identifier | http://hdl.handle.net/10722/322041 |
ISBN | |
ISSN | 2020 SCImago Journal Rankings: 0.249 |
ISI Accession Number ID | |
Series/Report no. | Lecture Notes in Computer Science ; 9907 LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Jun | - |
dc.contributor.author | Shahroudy, Amir | - |
dc.contributor.author | Xu, Dong | - |
dc.contributor.author | Wang, Gang | - |
dc.date.accessioned | 2022-11-03T02:23:12Z | - |
dc.date.available | 2022-11-03T02:23:12Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 11-14 October 2016. In Leibe, B, Matas, J, Sebe, N, et al. (Eds.), Computer Vision - ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III, p. 816-833. Cham: Springer, 2016 | - |
dc.identifier.isbn | 9783319464862 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/322041 | - |
dc.description.abstract | 3D action recognition–analysis of human actions based on 3D skeleton data–becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based learning methods to model the contextual dependency in the temporal domain. In this paper, we extend this idea to spatio-temporal domains to analyze the hidden sources of action-related information within the input data over both domains concurrently. Inspired by the graphical structure of the human skeleton, we further propose a more powerful tree-structure based traversal method. To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell. Our method achieves state-of-the-art performance on 4 challenging benchmark datasets for 3D human action analysis. | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Computer Vision - ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 9907 | - |
dc.relation.ispartofseries | LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics | - |
dc.subject | 3D action recognition | - |
dc.subject | Long short-term memory | - |
dc.subject | Recurrent neural networks | - |
dc.subject | Spatio-temporal analysis | - |
dc.subject | Trust gate | - |
dc.title | Spatio-temporal LSTM with trust gates for 3D human action recognition | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-319-46487-9_50 | - |
dc.identifier.scopus | eid_2-s2.0-84990059379 | - |
dc.identifier.spage | 816 | - |
dc.identifier.epage | 833 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.identifier.isi | WOS:000389384800050 | - |
dc.publisher.place | Cham | - |