A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

C Sahin, G Garcia-Hernando, J Sock, TK Kim - Image and Vision …, 2020 - Elsevier
Object pose recovery has gained increasing attention in the computer vision field as it has
become an important problem in rapidly evolving technological areas related to autonomous …

Scalable action recognition with a subspace forest

S O'Hara, BA Draper - 2012 IEEE Conference on Computer …, 2012 - ieeexplore.ieee.org
We present a novel structure, called a Subspace Forest, designed to provide an efficient
approximate nearest neighbor query of subspaces represented as points on Grassmann …

Survey: How good are the current advances in image set based face identification?–Experiments on three popular benchmarks with a naïve approach

L Chen, N Hassanpour - Computer Vision and Image Understanding, 2017 - Elsevier
The recent proposed approaches on image set based face identification always follow a four-
stage pipeline: face detection–face image representation–face image set modelling …

[PDF][PDF] 基于L1 范数凸包数据描述的多观测样本分类算法

胡正平, 王玲丽 - 电子与信息学报, 2012 - edit.jeit.ac.cn
为建立高维空间样本分布的最佳覆盖为目标来实现覆盖分类, 该文提出基于L1
范数凸包数据描述的多观测样本分类算法. 首先对训练集的每个类别以及测试集的多观测样本 …

[图书][B] Scalable learning of actions from unlabeled videos

S O'Hara - 2013 - search.proquest.com
Emerging applications in human-computer interfaces, security, and robotics have a need for
understanding human behavior from video data. Much of the research in the field of action …

Pattern change discovery between high dimensional data sets

Y Xu, ZM Zhang - US Patent App. 18/441,887, 2024 - Google Patents
The general problem of pattern change discovery between high-dimensional data sets is
addressed by considering the notion of the principal angles between the subspaces is …

[引用][C] 基于Kernel Discriminant Canonical Correlation (KDCC) 的多观测样本分类算法

牛晓霞, 胡正平, 王玲丽 - 数学的实践与认识, 2012