L
Litong Feng
Researcher at SenseTime
Publications - 55
Citations - 1261
Litong Feng is an academic researcher from SenseTime. The author has contributed to research in topics: Feature extraction & Computer science. The author has an hindex of 14, co-authored 51 publications receiving 888 citations. Previous affiliations of Litong Feng include City University of Hong Kong.
Papers
More filters
Journal ArticleDOI
Integration of image quality and motion cues for face anti-spoofing
TL;DR: An extendable multi-cues integration framework for face anti-spoofing using a hierarchical neural network is proposed, which can fuse image quality cues and motion cues for liveness detection.
Journal ArticleDOI
Motion-Resistant Remote Imaging Photoplethysmography Based on the Optical Properties of Skin
TL;DR: Experimental results show that the proposed RIPPG can obtain greatly improved performance in accessing heart rates in moving subjects, compared with the state-of-the-art facial video-based RIPPG methods.
Journal ArticleDOI
No-Reference Video Quality Assessment With 3D Shearlet Transform and Convolutional Neural Networks
TL;DR: This paper proposes an efficient general-purpose no-reference video quality assessment (VQA) framework that is based on 3D shearlet transform and convolutional neural network and demonstrates that SACONVA performs well in predicting video quality and is competitive with current state-of-the-art full-reference VQA methods and general- Purpose NR-VQ a algorithms.
Journal ArticleDOI
No-reference image quality assessment with shearlet transform and deep neural networks
TL;DR: A general-purpose no-reference (NR) image quality assessment (IQA) framework based on deep neural network is presented and insight is given into the operation of this network and intuitive explanations of how it works and why it works well are given.
Proceedings ArticleDOI
Scale-Equalizing Pyramid Convolution for Object Detection
TL;DR: Jeon et al. as mentioned in this paper proposed a scale-equalizing pyramid convolution (SEPC) that aligns the shared pyramid convolutions kernel only at high-level feature maps to extract scale-invariant features.