Recognizing human actions as the evolution of pose estimation maps
Most video-based action recognition approaches choose to extract features from the whole video to recognize actions. The cluttered background and non-action motions limit the performances of these methods, since they lack the explicit modeling of human body movements. With recent advances of human p...
Main Authors: | Liu, Mengyuan, Yuan, Junsong |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/143208 |
Similar Items
-
Deformable pose traversal convolution for 3D action and gesture recognition
by: Weng, Junwu, et al.
Published: (2020) -
Egocentric hand pose estimation and distance recovery in a single RGB image
by: Liang, Hui, et al.
Published: (2016) -
Scaling up parametric human recovery
by: Cai, Zhongang
Published: (2024) -
Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks
by: Cai, Yujun, et al.
Published: (2019) -
Toward human-centered automated driving: a novel spatiotemporal vision transformer-enabled head tracker
by: Hu, Zhongxu, et al.
Published: (2022)