H
Hao Li
Researcher at Alibaba Group
Publications - 225
Citations - 14999
Hao Li is an academic researcher from Alibaba Group. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 56, co-authored 221 publications receiving 10232 citations. Previous affiliations of Hao Li include University of Southern California & Institute for Creative Technologies.
Papers
More filters
Proceedings ArticleDOI
Volumetric human teleportation
TL;DR: This work introduces the first system that can capture a completely clothed human body (including the back) using a single RGB webcam and in real time and enables new possibilities for low-cost and consumeraccessible immersive teleportation.
Posted Content
Neural Architecture Design for GPU-Efficient Networks
TL;DR: This work proposes a general principle for designing GPU-efficient networks based on extensive empirical studies, and designs a family of GPU-Efficient Networks, or GENets in short, which outperforms most state-of-the-art models that are more efficient than EfficientNet in high precision regimes.
Proceedings ArticleDOI
Exploring the Quality of GAN Generated Images for Person Re-Identification
TL;DR: Zhang et al. as mentioned in this paper analyzed the in-depth characteristics of ReID sample and solved the problem of "What makes a GAN-generated image good for ReID" by examining each data sample with idconsistency and diversity constraints by mapping image onto different spaces.
Journal ArticleDOI
Patient-specific assessment of dysmorphism of the femoral head–neck junction: a statistical shape model approach
Vikas Khanduja,Vikas Khanduja,N Baelde,Andreas Dobbelaere,Jan Van Houcke,Hao Li,Christophe Pattyn,Emmanuel Audenaert +7 more
TL;DR: Objective quantification of anatomical variations about the femur head–neck junction in pre‐operative planning for surgical intervention in femoro‐acetabular impingement is problematic, as no clear definition of average normal anatomy for a specific subject exists.
Proceedings ArticleDOI
Dynamic Geometry Processing
TL;DR: This tutorial on ŞDynamic Geometry Processing considers the problem of processing such dynamic range data effectively and efficiently and introduces basic processing techniques for analyzing and matching range data.