Unsupervised deep generative adversarial hashing network

KG Dizaji, F Zheng, N Sadoughi… - Proceedings of the …, 2018 - openaccess.thecvf.com
Unsupervised deep hash functions have not shown satisfactory improvements against the
shallow alternatives, and usually, require supervised pretraining to avoid getting stuck in …

Direct shape regression networks for end-to-end face alignment

X Miao, X Zhen, X Liu, C Deng… - Proceedings of the …, 2018 - openaccess.thecvf.com
Face alignment has been extensively studied in computer vision community due to its
fundamental role in facial analysis, but it remains an unsolved problem. The major …

Sparse Index Tracking With K-Sparsity or ϵ-Deviation Constraint via ℓ0-Norm Minimization

XP Li, ZL Shi, CS Leung, HC So - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
Sparse index tracking, as one of the passive investment strategies, is to track a benchmark
financial index via constructing a portfolio with a few assets in a market index. It can be …

Application of machine learning for high-throughput tumor marker screening

X Fu, W Ma, Q Zuo, Y Qi, S Zhang, Y Zhao - Life Sciences, 2024 - Elsevier
High-throughput sequencing and multiomics technologies have allowed increasing
numbers of biomarkers to be mined and used for disease diagnosis, risk stratification …

Multi-output soft sensor modeling approach for penicillin fermentation process based on features of big data

L Li, N Li, X Wang, J Zhao, H Zhang, T Jiao - Expert Systems with …, 2023 - Elsevier
The product quality indicators of the penicillin fermentation process have multiple semantics
and are interrelated. There is a complex nonlinear mapping relationship between input …

Discriminative sparse embedding based on adaptive graph for dimension reduction

Z Liu, K Shi, K Zhang, W Ou, L Wang - Engineering Applications of Artificial …, 2020 - Elsevier
The traditional manifold learning methods usually utilize the original observed data to
directly define the intrinsic structure among data. Because the original samples often contain …

Feature selection based on regularization of sparsity based regression models by hesitant fuzzy correlation

M Mokhtia, M Eftekhari, F Saberi-Movahed - Applied Soft Computing, 2020 - Elsevier
In this paper, the Ridge, LASSO and Elastic Net regression methods are adapted for the task
of selecting feature. In order to enhance the feature selection performance via these …

In defense of single-column networks for crowd counting

Z Wang, Z Xiao, K Xie, Q Qiu, X Zhen, X Cao - arXiv preprint arXiv …, 2018 - arxiv.org
Crowd counting usually addressed by density estimation becomes an increasingly important
topic in computer vision due to its widespread applications in video surveillance, urban …

[HTML][HTML] Bayesian learning of feature spaces for multitask regression

C Sevilla-Salcedo, A Gallardo-Antolín… - Neural Networks, 2024 - Elsevier
This paper introduces a novel approach to learn multi-task regression models with
constrained architecture complexity. The proposed model, named RFF-BLR, consists of a …

[PDF][PDF] Attentional Alignment Networks.

L Yue, X Miao, P Wang, B Zhang, X Zhen, X Cao - BMVC, 2018 - bmva-archive.org.uk
Face alignment has recently generated great popularity in computer vision due to its
widespread applications. The cascaded regression model has dominated and achieved …