51 citations · 53 across the 2 of their papers we have counts for
5 papers · 1 filter
Exploiting Spatial-temporal Correlations for Video Anomaly Detection
Mengyang Zhao, Yang Liu, Jing Li +1
Video anomaly detection (VAD) remains a challenging task in the pattern recognition community due to the ambiguity and diversity of abnormal events. Existing deep learning-based VA…
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…
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…
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…
Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition
Yang Liu, Zhaoyang Lu, Jing Li +1
Recognizing human actions from varied views is challenging due to huge appearance variations in different views. The key to this problem is to learn discriminant view-invariant rep…