Kejun Wang
Harbin Engineering University
15 Papers
66 Citations
Kejun Wang is an academic researcher from Harbin Engineering University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 6, co-authored 15 publications.
Chat about Author
Papers
HEU Emotion: A Large-scale Database for Multi-modal Emotion Recognition in the Wild
Jing Chen,Chenhui Wang,Kejun Wang,Chaoqun Yin,Cong Zhao,Tao Xu,Xinyi Zhang,Ziqiang Huang,Meichen Liu,Tao Yang +9 more
TL;DR: This work collected, annotated, and prepared to release a new natural state video database, HEU Emotion, which is by far the most extensive multi-modal emotional database with 9,951 subjects, and used many conventional machine learning and deep learning methods to evaluate Heu Emotion.
49
An improved biometrics technique based on metric learning approach
TL;DR: A biometrics technique based on metric learning approach is proposed to achieve higher correct classification rates under the condition that the feature of the query is very different from that of the register for a given individual.
40
Kernel coupled distance metric learning for gait recognition and face recognition
TL;DR: The problem of kernel coupled distance metric learning is formulated as an optimization problem whose aims are to search for the pair-wise samples staying as close as possible and to preserve the local structure intrinsic data geometry.
40
A novel GCM chaotic neural network for information processing
Tao Wang,Nuo Jia,Kejun Wang +2 more
TL;DR: A new chaotic neural network named “globally coupled map using sine map(SI-GCM)”, which is a modified Kaneko’s globally coupled map model, is proposed, which exhibits rich dynamic behaviors.
13
Sequential convolutional network for behavioral pattern extraction in gait recognition
TL;DR: Wang et al. as mentioned in this paper proposed a sequential convolutional network (SCN) from a novel perspective, where spatiotemporal features can be learned by a basic CNN backbone and behavioral information extractors (BIE) are constructed to comprehend intermediate feature maps in time series through motion templates where the relation between frames can be analyzed, thereby distilling the information of the walking pattern.
12