51 citations · 51 across the 1 of their papers we have counts for
3 papers
cs.CV2019★ 51 cited
Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition
Yang Liu, Zhaoyang Lu, Jing Li +2
Existing deep learning methods for action recognition in videos require a large number of labeled videos for training, which is labor-intensive and time-consuming. For the same act…
cs.CV2019
Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
Yang Liu, Zhaoyang Lu, Jing Li +2
Recently, infrared human action recognition has attracted increasing attention for it has many advantages over visible light, that is, being robust to illumination change and shado…
cs.CV2019
Global Temporal Representation based CNNs for Infrared Action Recognition
Yang Liu, Zhaoyang Lu, Jing Li +2
Infrared human action recognition has many advantages, i.e., it is insensitive to illumination change, appearance variability, and shadows. Existing methods for infrared action rec…