W
Wei Wang
Researcher at National University of Singapore
Publications - 653
Citations - 24737
Wei Wang is an academic researcher from National University of Singapore. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 69, co-authored 623 publications receiving 19639 citations. Previous affiliations of Wei Wang include Dongguan University of Technology & Commissariat à l'énergie atomique et aux énergies alternatives.
Papers
More filters
Proceedings ArticleDOI
Hierarchical recurrent neural network for skeleton based action recognition
Yong Du,Wei Wang,Liang Wang +2 more
TL;DR: This paper proposes an end-to-end hierarchical RNN for skeleton based action recognition, and demonstrates that the model achieves the state-of-the-art performance with high computational efficiency.
Journal ArticleDOI
Efficient similarity joins for near-duplicate detection
TL;DR: This article proposes new filtering techniques by exploiting the token ordering information and drastically reduce the candidate sizes and hence improve the efficiency of existing algorithms to find a pair of records such that their similarities are no less than a given threshold.
Proceedings ArticleDOI
Efficient similarity joins for near duplicate detection
TL;DR: This paper proposes new filtering techniques by exploiting the ordering information and drastically reduce the candidate sizes and improve the efficiency of existing algorithms to find pairs of records such that their similarities are above a given threshold.
Proceedings ArticleDOI
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
TL;DR: Zhang et al. as mentioned in this paper proposed an attention enhanced graph convolutional LSTM network (AGC-LSTM) for human action recognition from skeleton data, which can not only capture discriminative features in spatial configuration and temporal dynamics but also explore the co-occurrence relationship between spatial and temporal domains.
Proceedings ArticleDOI
Utility-based anonymization using local recoding
TL;DR: This paper proposes a simple framework to specify utility of attributes and develops two simple yet efficient heuristic local recoding methods for utility-based anonymization, which outperform the state-of-the-art multidimensional global recode methods in both discernability and query answering accuracy.