A review on machine learning styles in computer vision—techniques and future directions
Computer applications have considerably shifted from single data processing to machine
learning in recent years due to the accessibility and availability of massive volumes of data …
learning in recent years due to the accessibility and availability of massive volumes of data …
Online multi-class LPBoost
Online boosting is one of the most successful online learning algorithms in computer vision.
While many challenging online learning problems are inherently multi-class, online boosting …
While many challenging online learning problems are inherently multi-class, online boosting …
Object categorization
A Pinz - Foundations and Trends® in Computer Graphics …, 2006 - nowpublishers.com
This paper presents foundations, original research and trends in the field of object
categorization by computer vision methods. The research goals in object categorization are …
categorization by computer vision methods. The research goals in object categorization are …
Online crowdsourcing subjective image quality assessment
Recently, HodgeRank on random graphs has been proposed as an effective framework for
multimedia quality assessment problem based on paired comparison method. With the …
multimedia quality assessment problem based on paired comparison method. With the …
Bi-directional pptical flow for future video codec
A Alshin, E Alshina - 2016 Data Compression Conference …, 2016 - ieeexplore.ieee.org
Paper presents theoretical explanation for bi-directional optical flow technique in generic
case. Both non-equal distance to reference frames and two reference frames from the same …
case. Both non-equal distance to reference frames and two reference frames from the same …
Determining and utilizing corrections to robot actions
N Hudson, D Yamparala - US Patent 10,562,181, 2020 - Google Patents
The present disclosure is directed to methods, apparatus, and computer-readable media
(transitory and non-transitory) for determining and utilizing human corrections to robot …
(transitory and non-transitory) for determining and utilizing human corrections to robot …
Human–machine interaction issues in quality control based on online image classification
This paper considers on a number of issues that arise when a trainable machine vision
system learns directly from humans. We contrast this to the “normal” situation where …
system learns directly from humans. We contrast this to the “normal” situation where …
Update of local features model based on correction to robot action
Methods, apparatus, and computer-readable media for determining and utilizing corrections
to robot actions. Some implementations are directed to updating a local features model of a …
to robot actions. Some implementations are directed to updating a local features model of a …
A biologically motivated visual memory architecture for online learning of objects
S Kirstein, H Wersing, E Körner - Neural Networks, 2008 - Elsevier
We present a biologically motivated architecture for object recognition that is based on a
hierarchical feature-detection model in combination with a memory architecture that …
hierarchical feature-detection model in combination with a memory architecture that …
Online learning of objects in a biologically motivated visual architecture
H Wersing, S Kirstein, M Götting, H Brandl… - … Journal of Neural …, 2007 - World Scientific
We present a biologically motivated architecture for object recognition that is capable of
online learning of several objects based on interaction with a human teacher. The system …
online learning of several objects based on interaction with a human teacher. The system …