Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally

Jia, Xiuyi; Zheng, Xiang; Li, Weiwei; Zhang, Changqing; Li, Zechao

doi:10.1109/cvpr.2019.01007

Cited by 65 publications

(48 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem transformation strategy transforms the LDL problem into an existing learning paradigm. The PT-Bayes [3] and PT-SVM [21] methods transform the label distribution into weighted single-label examples so that a single-label learning framework can be used. PT-Bayes uses Bayes' rule to calculate the description degree of corresponding label and PT-SVM uses a pairwise coupling method to obtain the label distribution.…”

Section: B Ldl Methodsmentioning

confidence: 99%

“…The designs generally focus on three aspects: the output model, objective function, and optimization method. The maximum entropy model [3], [4], [21], [23]- [28] is usually employed as the output model. The optimization methods include the strategy similar to Improved Iterative Scaling (IIS) [3], the effective quasi-Newton method (BFGS) [3], [25], and the Alternating Direction Method of Multipliers (ADMM) [4], [29], etc.…”

Section: B Ldl Methodsmentioning

confidence: 99%

See 1 more Smart Citation

COS-LDL: Label Distribution Learning by Cosine-Based Distance-Mapping Correlation

Zhang

Huang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Label distribution learning (LDL) is a popular research trend in multi-label learning. Competing methods have been designed to improve the predictive performance. In this paper, we propose a method called cosine-based correlation for LDL (COS-LDL). The key issue is how to exploit correlations among different labels of the same instance. We propose a distance-mapping function for this purpose. With this mapping function, we design an objective function and its corresponding learning algorithm. Experiments undertaken on thirteen real-world datasets compare with eight LDL state-of-the-art methods. Results demonstrate that COS-LDL outperforms them in eight out of ten popular measures. INDEX TERMS Cosine similarity, distance-mapping matrix, label correlation, label distribution learning. I. INTRODUCTION Label distribution learning (LDL) [1]-[6] is a generalization of multi-label learning (MLL) [7]-[13]. It was first presented by Geng [3]. Unlike traditional MLL, which outputs a label set, LDL outputs a label distribution. MLL handles the ambiguity of ''what describes the instance.'' In contrast, LDL [3] deals with the more general ambiguity of ''how to describe the instance.'' Figure 1(a) is an image of the sea [14]. Figure 1(b) shows the labels city and sea obtained by MLL, and Fig. 1(c) shows the distribution of the four labels obtained by LDL. Naturally, LDL provides richer information than does MLL. LDL methods are gaining increasing attention in areas such as soft video parsing [15], age estimation [16]-[19], and crowd counting [20]. Various LDL methods have been designed to improve the predictive performance [3], [21], [22]. Geng [3] proposed the IIS-LLD method by transforming the single-label data into distribution data. This method does not consider the correlations among the labels. Jia et al. [21] introduced Pearson's correlation coefficients to describe label correlations. The associate editor coordinating the review of this manuscript and approving it for publication was Juan Wang .

show abstract

Section: B Ldl Methodsmentioning

confidence: 99%

Section: B Ldl Methodsmentioning

confidence: 99%

COS-LDL: Label Distribution Learning by Cosine-Based Distance-Mapping Correlation

Zhang

Huang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…We first introduce some related concepts and notations of tensors used throughout of the paper. More details about tensor algebra, please refer to [Kolda and Bader, 2009]. The order of a tensor is the number of dimensions, also known as modes.…”

Section: Notation and Backgroundmentioning

confidence: 99%

“…Therefore, we add the l 2,1 -regularization on H to make it row-sparse. According to [Kolda and Bader, 2009], CP factorization can be written in the following matricized form:…”

Section: Construct Common Representationmentioning

confidence: 99%

“…In real-world applications, label correlations are usually local, where a label correlation may be shared by only a subset of instances rather than all instances. So we adopt a low-rank structure to implicitly exploit the label correlations at the local level [Jia et al, 2019]. The training set is divided into k clusters and each cluster has a low-rank structure,…”

Section: Label Enhancementmentioning

confidence: 99%

See 1 more Smart Citation

Tensor-based multi-view label enhancement for multi-label learning

Zhang

Jia

2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Label enhancement (LE) is a procedure of recovering the label distributions from the logical labels in the multi-label data, the purpose of which is to better represent and mine the label ambiguity problem through the form of label distribution. Existing LE work mainly concentrates on how to leverage the topological information of the feature space and the correlation among the labels, and all are based on single view data. In view of the fact that there are many multi-view data in real-world applications, which can provide richer semantic information from different perspectives, this paper first presents a multi-view label enhancement problem and proposes a tensor-based multi-view label enhancement method, named TMV-LE. Firstly, we introduce the tensor factorization to get the common subspace which contains the high-order relationships among different views. Secondly, we use the common representation and multiple views to jointly mine a more comprehensive topological structure in the dataset. Finally, the topological structure of the feature space is migrated to the label space to get the label distributions. Extensive comparative studies validate that the performance of multi-view multi-label learning can be improved significantly with TMV-LE.

show abstract

SPL-MLL: Selecting Predictable Landmarks for Multi-label Learning

Zhang

Zhu

et al. 2020

Computer Vision – ECCV 2020

View full text Add to dashboard Cite

Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally

Cited by 65 publications

References 27 publications

COS-LDL: Label Distribution Learning by Cosine-Based Distance-Mapping Correlation

COS-LDL: Label Distribution Learning by Cosine-Based Distance-Mapping Correlation

Tensor-based multi-view label enhancement for multi-label learning

SPL-MLL: Selecting Predictable Landmarks for Multi-label Learning

Contact Info

Product

Resources

About