Sökning: L773:9781665487399 OR L773:9781665487405 >
Bootstrapped Repres...
Bootstrapped Representation Learning for Skeleton-Based Action Recognition
-
- Moliner, Olivier (författare)
- Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH,Sony Europe B.V.
-
- Huang, Sangxia (författare)
- Sony Europe B.V.
-
- Astrom, Kalle (författare)
- Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,LTH profilområde: AI och digitalisering,LTH profilområden,LTH profilområde: Teknik för hälsa,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH,LTH Profile Area: Engineering Health,Faculty of Engineering, LTH,Sony Europe B.V.
-
(creator_code:org_t)
- 2022
- 2022
- Engelska 11 s.
-
Ingår i: Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022. - 2160-7508 .- 2160-7516. - 9781665487399 ; 2022-June, s. 4153-4163
- Relaterad länk:
-
http://dx.doi.org/10...
-
visa fler...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on skeleton sequence data and propose a new data augmentation strategy including two asymmetric transformation pipelines. We also introduce a multi-viewpoint sampling method that leverages multiple viewing angles of the same action captured by different cameras. In the semi-supervised setting, we show that the performance can be further improved by knowledge distillation from wider networks, leveraging once more the unlabeled samples. We conduct extensive experiments on the NTU-60, NTU-120 and PKU-MMD datasets to demonstrate the performance of our proposed method. Our method consistently outperforms the current state of the art on linear evaluation, semi-supervised and transfer learning benchmarks.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas