C
Cuiling Lan
Researcher at Microsoft
Publications - 99
Citations - 6377
Cuiling Lan is an academic researcher from Microsoft. The author has contributed to research in topics: Feature (computer vision) & Recurrent neural network. The author has an hindex of 23, co-authored 99 publications receiving 3758 citations. Previous affiliations of Cuiling Lan include Xi'an Jiaotong University & University of Science and Technology of China.
Papers
More filters
Posted Content
Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks
TL;DR: This work takes the skeleton as the input at each time slot and introduces a novel regularization scheme to learn the co-occurrence features of skeleton joints, and proposes a new dropout algorithm which simultaneously operates on the gates, cells, and output responses of the LSTM neurons.
Proceedings Article
An end-to-end spatio-temporal attention model for human action recognition from skeleton data
TL;DR: Zhang et al. as mentioned in this paper proposed an end-to-end spatial and temporal attention model for human action recognition from skeleton data, which learns to selectively focus on discriminative joints of skeleton within each frame of the inputs and pays different levels of attention to the outputs of different frames.
Proceedings ArticleDOI
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
TL;DR: Zhang et al. as discussed by the authors proposed a view adaptive recurrent neural network (RNN) with LSTM architecture, which enables the network itself to adapt to the most suitable observation viewpoints from end to end.
Posted Content
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
TL;DR: A novel view adaptation scheme to automatically regulate observation viewpoints during the occurrence of an action by design a view adaptive recurrent neural network with LSTM architecture, which enables the network itself to adapt to the most suitable observation viewpoints from end to end.
Proceedings ArticleDOI
Relation-Aware Global Attention for Person Re-Identification
TL;DR: This work proposes an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning and proposes to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions together to learn the attention with a shallow convolutional model.