C
Chengyao Shen
Researcher at National University of Singapore
Publications - 11
Citations - 703
Chengyao Shen is an academic researcher from National University of Singapore. The author has contributed to research in topics: Deep learning & Fixation (visual). The author has an hindex of 5, co-authored 11 publications receiving 596 citations.
Papers
More filters
Proceedings ArticleDOI
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
TL;DR: This paper presents a focused study to narrow the semantic gap with an architecture based on Deep Neural Network (DNN), which leverages the representational power of high-level semantics encoded in DNNs pretrained for object recognition.
Journal ArticleDOI
Learning to predict eye fixations for semantic contents using multi-layer sparse network
Chengyao Shen,Qi Zhao +1 more
TL;DR: A novel model for saliency prediction under a unified framework of feature integration that distinguishes itself by directly learning from natural images and automatically incorporating higher-level semantic information in a scalable manner for gaze prediction.
Journal ArticleDOI
Predicting Eye Fixations on Webpage With an Ensemble of Early Features and High-Level Representations from Deep Network
Chengyao Shen,Xun Huang,Qi Zhao +2 more
TL;DR: This study utilizes a new scheme of low-level feature extraction pipeline and combines it with high-level representations from deep neural networks and shows that the model outperforms other existing saliency models by a large margin and both low- and high- level features play an important role in predicting fixations on webpage.
Proceedings ArticleDOI
Ultrasound guided automatic localization of needle insertion site for epidural anesthesia
TL;DR: A modified version of local normalization using the Difference of Gaussian algorithm is first used for pre-processing to filter the speckle noise and extract the main anatomical structure in the raw images obtained and this approach has been tested on more than 200 ultrasound images with a 100% success rate.
Journal ArticleDOI
Geometrically local embedding in manifolds for dimension reduction
TL;DR: Geometrically local embedding is presented to discover the intrinsic structure of manifolds as a method in nonlinear dimension reduction and proves the effectiveness of GLE in dimension reduction, feature extraction, data visualization as well as clustering and classification.