Binary Relevance is a well-known framework for multi-label classification, which considers each class label as a binary classification problem. Many existing multi-label algorithms are constructed within this framework, and utilize identical data representation in the discrimination of all the class labels. In multi-label classification, however, each class label might be determined by some specific characteristics of its own. In this paper, we seek to learn label-specific data representation for each class label, which is composed of label-specific features. Our proposed method LLSF can not only be utilized for multi-label classification directly, but also be applied as a feature selection method for multi-label learning and a general strategy to improve multi-label classification algorithms comprising a number of binary classifiers. Inspired by the research works on modeling high-order label correlations, we further extend LLSF to learn class-Dependent Labels in a sparse stackingway, denoted as LLSF-DL. It incorporates both second-order- and high-order label correlations. A comparative study with the state-of-the-art approaches manifests the effectiveness and efficiency of our proposed methods.

Multilabel learning deals with examples having multiple class labels simultaneously. It has been applied to a variety of applications, such as text categorization and image annotation. A large number of algorithms have been proposed for multilabel learning, most of which concentrate on multilabel classification problems and only a few of them are feature selection algorithms. Current multilabel classification models are mainly built on a single data representation composed of all the features which are shared by all the class labels. Since each class label might be decided by some specific features of its own, and the problems of classification and feature selection are often addressed independently, in this paper, we propose a novel method which can perform joint feature selection and classification for multilabel learning, named JFSC. Different from many existing methods, JFSC learns both shared features and label-specific features by considering pairwise label correlations, and builds the multilabel classifier on the learned low-dimensional data representations simultaneously. A comparative study with state-of-the-art approaches manifests a competitive performance of our proposed method both in classification and feature selection for multilabel learning.

With the development of hyperspectral sensing technology, hyperspectral target detection technology plays an important role in remote target detection. However, existing hyperspectral target detection models are poorly adapted to complex backgrounds and mainly focus on the spectral domain, making less use of spatial structure information leading to low target detection rates. Therefore, a new target detection algorithm based on the prior spectral perception and local graph fusion (SPLGF) is proposed. Firstly, the prior spectrum-guided target extraction method is established. This method can take full advantage of the background and target spectral information by local inner and outer window linkage, reduce the impact of spectral variability on target acquisition performance, and improve detection stability. Secondly, the target enhancement strategy based on the Gabor multi-feature graph is proposed. This technique makes full use of multi-directional and multi-scale spatial information, which can reduce the influence of brightness, contrast and amplitude variation on detection performance due to light and angle. Finally, spatial-spectral fusion is executed to achieve target detection. It can make full use of spectral and spatial structure information to improve the target detection effect. Publicly available datasets and real collected datasets are adopted to check the validity of the proposed method. After comparison, it is found that the proposed algorithm has better detection effect than existing baseline methods. The maximum improvement in AUC values are 16.56%-88.16% across the eight datasets.

Since Electroencephalogram (EEG) is resistant to camouflage, it has been a reliable data source for objective emotion recognition. EEG is naturally multi-rhythm and multi-channel, based on which we can extract multiple features for further processing. In EEG-based emotion recognition, it is important to investigate whether there exist some common features shared by different emotional states, and the specific features associated with each emotional state. However, such fundamental problem is ignored by most of the existing studies. To this end, we propose a Joint label-Common and label-Specific Features Exploration (JCSFE) model for semi-supervised cross-session EEG emotion recognition in this paper. To be specific, JCSFE imposes the ℓ _2,1 -norm on the projection matrix to explore the label-common EEG features and simultaneously the ℓ ₁ -norm is used to explore the label-specific EEG features. Besides, a graph regularization term is introduced to enforce the data local invariance property, i.e ., similar EEG samples are encouraged to have the same emotional state. Results obtained from the SEED-IV and SEED-V emotional data sets experimentally demonstrate that JCSFE not only achieves superior emotion recognition performance in comparison with the state-of-the-art models but also provides us with a quantitative method to identify the label-common and label-specific EEG features in emotion recognition.