File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TCSVT.2022.3197395
- Scopus: eid_2-s2.0-85136143540
- WOS: WOS:000936985600049
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: 3D-Pruning: A Model Compression Framework for Efficient 3D Action Recognition
Title | 3D-Pruning: A Model Compression Framework for Efficient 3D Action Recognition |
---|---|
Authors | |
Keywords | 3D action recognition Computational complexity Computational modeling Efficient deep learning Feature extraction model compression point cloud Point cloud compression Solid modeling Task analysis Three-dimensional displays |
Issue Date | 2022 |
Citation | IEEE Transactions on Circuits and Systems for Video Technology, 2022 How to Cite? |
Abstract | The existing end-to-end optimized 3D action recognition methods often suffer from high computational complexity burden. Observing that different frames and different points in point cloud sequences often have different importance values for the 3D action recognition task, in this work, we propose a fully automatic model compression framework called 3D-Pruning (3DP) for efficient 3D action recognition. After model compression by using our 3DP framework, the compressed model can process different frames and different points in each frame by using different computational complexities based on their importance values, in which both the importance value and computational complexity for each frame/point can be automatically learned. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our 3DP framework for model compression. |
Persistent Identifier | http://hdl.handle.net/10722/322004 |
ISSN | 2023 Impact Factor: 8.3 2023 SCImago Journal Rankings: 2.299 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Guo, Jinyang | - |
dc.contributor.author | Liu, Jiaheng | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:22:57Z | - |
dc.date.available | 2022-11-03T02:22:57Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | IEEE Transactions on Circuits and Systems for Video Technology, 2022 | - |
dc.identifier.issn | 1051-8215 | - |
dc.identifier.uri | http://hdl.handle.net/10722/322004 | - |
dc.description.abstract | The existing end-to-end optimized 3D action recognition methods often suffer from high computational complexity burden. Observing that different frames and different points in point cloud sequences often have different importance values for the 3D action recognition task, in this work, we propose a fully automatic model compression framework called 3D-Pruning (3DP) for efficient 3D action recognition. After model compression by using our 3DP framework, the compressed model can process different frames and different points in each frame by using different computational complexities based on their importance values, in which both the importance value and computational complexity for each frame/point can be automatically learned. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our 3DP framework for model compression. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Circuits and Systems for Video Technology | - |
dc.subject | 3D action recognition | - |
dc.subject | Computational complexity | - |
dc.subject | Computational modeling | - |
dc.subject | Efficient deep learning | - |
dc.subject | Feature extraction | - |
dc.subject | model compression | - |
dc.subject | point cloud | - |
dc.subject | Point cloud compression | - |
dc.subject | Solid modeling | - |
dc.subject | Task analysis | - |
dc.subject | Three-dimensional displays | - |
dc.title | 3D-Pruning: A Model Compression Framework for Efficient 3D Action Recognition | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TCSVT.2022.3197395 | - |
dc.identifier.scopus | eid_2-s2.0-85136143540 | - |
dc.identifier.eissn | 1558-2205 | - |
dc.identifier.isi | WOS:000936985600049 | - |