K
Kebin Jia
Researcher at Beijing University of Technology
Publications - 151
Citations - 1425
Kebin Jia is an academic researcher from Beijing University of Technology. The author has contributed to research in topics: Computer science & Coding tree unit. The author has an hindex of 15, co-authored 130 publications receiving 957 citations.
Papers
More filters
Journal ArticleDOI
A Multi-View Deep Learning Framework for EEG Seizure Detection
TL;DR: A new autoencoder-based multi-view learning model is constructed by incorporating both inter and intra correlations of EEG channels to unleash the power of multi-channel information by adding a channel-wise competition mechanism in the training phase.
Journal ArticleDOI
Multiscale CNNs for Brain Tumor Segmentation and Diagnosis
Liya Zhao,Kebin Jia +1 more
TL;DR: An automatic brain tumor segmentation method based on Convolutional Neural Networks based on multiscale CNNs which could automatically detect the optimum top-three scales of the image sizes and combine information from different scale of the regions around that pixel.
Proceedings ArticleDOI
A Multi-view Deep Learning Method for Epileptic Seizure Detection using Short-time Fourier Transform
TL;DR: A multi-view deep learning model to capture brain abnormality from multi-channel epileptic EEG signals for seizure detection and is effective in detecting epileptic seizure is proposed.
Proceedings ArticleDOI
MuVAN: A Multi-view Attention Network for Multivariate Temporal Data
TL;DR: Experimental results show that the proposed MuVAN model outperforms the state-of-the-art deep representation approaches in different real-world tasks and can discover discriminative and meaningful attention scores across views over time, which improves the feature representation of multivariate temporal data.
Proceedings ArticleDOI
Deep Feature Learning with Discrimination Mechanism for Brain Tumor Segmentation and Diagnosis
Liya Zhao,Kebin Jia +1 more
TL;DR: It is proposed to construct different triplanar 2D CNNs architecture for 3D voxel classification, greatly reducing segmentation time, and accuracy, sensitivity and specificity are comparable in comparison with manual gold standard images and better than state-of-the-art segmentation methods.