Curriculum learning for multi-task classification of visual attributes

N Sarafianos, T Giannakopoulos… - Proceedings of the …, 2017 - openaccess.thecvf.com
Visual attributes, from simple objects to soft-biometrics have proven to be a powerful
representational approach for many applications such as image description and human …

An active multi-class classification using privileged information and belief function

M Javid, J Hamidzadeh - International Journal of Machine Learning and …, 2020 - Springer
Many classification models, based on support vector machine, have been designed so far to
improve classification performance in both supervised and semi-supervised learning. One of …

[PDF][PDF] Human activities recognition via smartphones using supervised machine learning classifiers

AY Shdefat, AA Halimeh, HC Kim - Prim Health Care, 2018 - researchgate.net
Human Activities Recognition Via Smartphones Using Supervised Machine Learning
Classifiers Page 1 Shdefat et al., Prim Health Care 2018, 8:1 DOI: 10.4172/2167-1079.1000289 …

Human activity recognition using robust adaptive privileged probabilistic learning

M Vrigkas, E Kazakos, C Nikou… - Pattern Analysis and …, 2021 - Springer
In this work, a supervised probabilistic approach is proposed that integrates the learning
using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) …

On the Capacity Limits of Privileged ERM

M Sharoni, S Sabato - International Conference on Artificial …, 2023 - proceedings.mlr.press
We study the supervised learning paradigm called Learning Using Privileged Information,
first suggested by Vapnik and Vashist (2009). In this paradigm, in addition to the examples …

Inferring human activities using robust privileged probabilistic learning

M Vrigkas, E Kazakos, C Nikou… - Proceedings of the …, 2017 - openaccess.thecvf.com
Classification models may often suffer from" structure imbalance" between training and
testing data that may occur due to the deficient data collection process. This imbalance can …

[图书][B] Domain Adaptation and Privileged Information for Visual Recognition

S Motiian - 2019 - search.proquest.com
The automatic identification of entities like objects, people or their actions in visual data,
such as images or video, has significantly improved, and is now being deployed in access …

Human Activity Recognition Using Robust Adaptive Privileged Probabilistic Learning

M Vrigkas, E Kazakos, C Nikou… - arXiv preprint arXiv …, 2017 - arxiv.org
In this work, a novel method based on the learning using privileged information (LUPI)
paradigm for recognizing complex human activities is proposed that handles missing …

[PDF][PDF] Robust Incremental Hidden Conditional Random Fields for Action Recognition

E Mastora - 2017 - cse.uoi.gr
Also, I would like to thank my fellow colleagues in the computer science department:
Michalis Vrigkas and Evangelos Kazakos, who contributed significantly throughout the …

[PDF][PDF] Robust incremental hidden conditional random fields for action recognition

Ε Μάστορα - 2017 - olympias.lib.uoi.gr
Also, I would like to thank my fellow colleagues in the computer science department:
Michalis Vrigkas and Evangelos Kazakos, who contributed significantly throughout the …