LAUSR

Deep subspace learning for expression recognition driven by a two-phase representation classifier

Sign Up to like & get
recommendations!
0 Published in 2020 at "Signal, Image and Video Processing"

DOI: 10.1007/s11760-019-01568-4

Abstract: Recent research has shown that the deep subspace learning (DSL) method can extract high-level features and better represent abstract semantics of data for facial expression recognition. While significant advances have been made in this area,… read more here.

Keywords: deep subspace; expression recognition; subspace learning; representation ... See more keywords

Multi-Scale Deep Subspace Clustering With Discriminative Learning

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE Access"

DOI: 10.1109/access.2022.3200482

Abstract: Deep subspace clustering methods have achieved impressive clustering performance compared with other clustering algorithms. However, most existing methods suffer from the following problems: 1) they only consider the global features but neglect the local features… read more here.

Keywords: multi scale; expressiveness coefficient; self expressiveness; subspace clustering ... See more keywords

Unsupervised Hyperspectral Image Band Selection Based on Deep Subspace Clustering

Sign Up to like & get
recommendations!
0 Published in 2019 at "IEEE Geoscience and Remote Sensing Letters"

DOI: 10.1109/lgrs.2019.2912170

Abstract: Hyperspectral image (HSI) consists of hundreds of continuous narrow bands with high redundancy, resulting in the curse of dimensionality and an increased computation complexity in HSI classification. Many clustering-based band selection approaches have been proposed… read more here.

Keywords: hyperspectral image; subspace clustering; band; band selection ... See more keywords

DSL-BC: Deep Subspace Learning with Boundary Consistency for Hyperspectral Image Classification

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE Transactions on Geoscience and Remote Sensing"

DOI: 10.1109/tgrs.2022.3177216

Abstract: Deep subspace learning (DSL) plays an essential role in hyperspectral image classification, providing an effective solution tool to reduce the redundant information of hyperspectral image (HSI) pixels. Semi-supervised convolutional neural network (CNN)-based DSL methods can… read more here.

Keywords: boundary consistency; classification; dsl; subspace ... See more keywords

Deep Subspace Clustering

Sign Up to like & get
recommendations!
1 Published in 2020 at "IEEE Transactions on Neural Networks and Learning Systems"

DOI: 10.1109/tnnls.2020.2968848

Abstract: In this article, we propose a deep extension of sparse subspace clustering, termed deep subspace clustering with L1-norm (DSC-L1). Regularized by the unit sphere distribution assumption for the learned deep features, DSC-L1 can infer a… read more here.

Keywords: assumption; neural networks; subspace clustering; subspace ... See more keywords