L
Li Liu
Researcher at National University of Defense Technology
Publications - 621
Citations - 19494
Li Liu is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Medicine & Computer science. The author has an hindex of 53, co-authored 411 publications receiving 11986 citations. Previous affiliations of Li Liu include Harvard University & University of the Sciences.
Papers
More filters
Journal ArticleDOI
Asymmetric Binary Coding for Image Search
TL;DR: A general binary coding framework based on asymmetric hash functions, named asymmetric inner-product binary coding (AIBC), which extends the AIBC approach to the supervised hashing scenario, where the inner products of learned binary codes are forced to fit the supervised similarities.
Journal ArticleDOI
Deep Video Super-Resolution Using HR Optical Flow Estimation
TL;DR: Wang et al. as mentioned in this paper proposed an end-to-end video super-resolution network to super-resolve both optical flows and images, which can exploit temporal dependency between consecutive frames.
Journal Article
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
TL;DR: Different architectures based on PyConv are presented for four main tasks on visual recognition: image classification, video action classification/recognition, object detection and semantic image segmentation/parsing, showing significant improvements over all these core tasks in comparison with the baselines.
Journal ArticleDOI
Association of Dietary Inflammatory Potential With Colorectal Cancer Risk in Men and Women.
Fred K. Tabung,Li Liu,Weike Wang,Teresa T. Fung,Teresa T. Fung,Kana Wu,Stephanie A. Smith-Warner,Yin Cao,Frank B. Hu,Frank B. Hu,Shuji Ogino,Shuji Ogino,Charles S. Fuchs,Charles S. Fuchs,Charles S. Fuchs,Edward Giovannucci,Edward Giovannucci +16 more
TL;DR: It is suggested that inflammation is a potential mechanism linking dietary patterns and colorectal cancer development and interventions to reduce the adverse role of proinflammatory diets may be more effective among overweight/obese men and lean women or men and women who do not consume alcohol.
Journal ArticleDOI
Zero-VAE-GAN: Generating Unseen Features for Generalized and Transductive Zero-Shot Learning
TL;DR: A joint generative model that couples variational autoencoder and generative adversarial network, called Zero-VAE-GAN, is proposed to generate high-quality unseen features and an adversarial categorization network is incorporated into the joint framework to enhance the class-level discriminability.