scispace - formally typeset
H

Hongdong Li

Researcher at Australian National University

Publications -  359
Citations -  14626

Hongdong Li is an academic researcher from Australian National University. The author has contributed to research in topics: Computer science & Motion estimation. The author has an hindex of 51, co-authored 306 publications receiving 10286 citations. Previous affiliations of Hongdong Li include NICTA & Vision Australia.

Papers
More filters
Book ChapterDOI

The Visual Object Tracking VOT2016 Challenge Results

Matej Kristan, +140 more
TL;DR: The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
Journal ArticleDOI

Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration

TL;DR: This paper presents the first globally optimal algorithm, named Go-ICP, for Euclidean (rigid) registration of two 3D point-sets under the inline-formula notation, and derives novel upper and lower bounds for the registration error function.
Proceedings ArticleDOI

Go-ICP: Solving 3D Registration Efficiently and Globally Optimally

TL;DR: This paper provides the very first globally optimal solution to Euclidean registration of two 3D point sets or two3D surfaces under the L2 error by exploiting the special structure of the underlying geometry.
Proceedings ArticleDOI

Neural Aggregation Network for Video Face Recognition

TL;DR: This NAN is trained with a standard classification or verification loss without any extra supervision signal, and it is found that it automatically learns to advocate high-quality face images while repelling low-quality ones such as blurred, occluded and improperly exposed faces.
Journal ArticleDOI

A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization

TL;DR: This paper proposes a simple “prior-free” method for solving the non-rigid structure-from-motion (NRSfM) factorization problem, which involves solving a very small SDP of fixed size, and a nuclear-norm minimization problem.