S
Shenghua Gao
Researcher at ShanghaiTech University
Publications - 172
Citations - 14462
Shenghua Gao is an academic researcher from ShanghaiTech University. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 40, co-authored 151 publications receiving 9083 citations. Previous affiliations of Shenghua Gao include Pennsylvania State University & Nanyang Technological University.
Papers
More filters
Proceedings ArticleDOI
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
TL;DR: With the proposed simple MCNN model, the method outperforms all existing methods and experiments show that the model, once trained on one dataset, can be readily transferred to a new dataset.
Journal ArticleDOI
PCANet: A Simple Deep Learning Baseline for Image Classification?
TL;DR: PCANet as discussed by the authors is a simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms.
Journal ArticleDOI
PCANet: A Simple Deep Learning Baseline for Image Classification?
TL;DR: Surprisingly, for all tasks, such a seemingly naive PCANet model is on par with the state-of-the-art features either prefixed, highly hand-crafted, or carefully learned [by deep neural networks (DNNs)].
Proceedings ArticleDOI
Future Frame Prediction for Anomaly Detection - A New Baseline
TL;DR: In this article, Liu et al. propose to detect abnormal events by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and this is the first work that introduces a temporal constraint into the video prediction task.
Journal ArticleDOI
CE-Net: Context Encoder Network for 2D Medical Image Segmentation
Zaiwang Gu,Jun Cheng,Huazhu Fu,Kang Zhou,Huaying Hao,Yitian Zhao,Tianyang Zhang,Shenghua Gao,Jiang Liu +8 more
TL;DR: Comprehensive results show that the proposed CE-Net method outperforms the original U- net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation , cell contour segmentation and retinal optical coherence tomography layer segmentation.