Developing the path signature methodology and its application to landmark-based human action recognition
Landmark-based human action recognition in videos is a challenging task in computer vision. One key step is to design a generic approach that generates discriminative features for the spatial structure and temporal dynamics. To this end, we regard the evolving landmark data as a high-dimensional pat...
Autors principals: | Yang, W, Lyons, T, Ni, H, Schmid, C, Jin, L |
---|---|
Format: | Journal article |
Idioma: | English |
Publicat: |
Springer
2022
|
Ítems similars
-
A path signature approach for speech emotion recognition
per: Wang, B, et al.
Publicat: (2019) -
Human Action Recognition in Unconstrained Trimmed Videos Using Residual Attention Network and Joints Path Signature
per: Tasweer Ahmad, et al.
Publicat: (2019-01-01) -
Rotation-free online handwritten character recognition using dyadic path signature features, hanging normalization, and deep neural network
per: Yang, W, et al.
Publicat: (2017) -
Inverting the signature of a path
per: Lyons, TJ, et al.
Publicat: (2018) -
Mobile landmark recognition
per: Eyu, Zhi Wei
Publicat: (2014)