Article
Biochemical Research Methods
Xiuquan Du, Jiajia Hu
Summary: In this study, a novel deep multi-label joint learning framework is proposed to leverage the relationship between multiple labels and binding proteins. A multi-label variant network is designed to explore multi-scale context hidden information, and a multi-label Long Short-Term Memory (multiLSTM) is used to mine the potential relationship between labels. Extensive experiments are carried out to compare the proposed method with other existing methods.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Yusheng Cheng, Qingyan Li, Yibin Wang, Weijie Zheng
Summary: This paper proposes a multi-view multi-label learning framework with view feature attention allocation, which improves the performance of multi-label prediction by distinguishing the importance of extracted features.
Article
Computer Science, Information Systems
Dawei Zhao, Qingwei Gao, Yixiang Lu, Dong Sun
Summary: This paper proposes a non-aligned multi-view multi-label classification method that learns view-specific labels and low-rank label structures in non-aligned views. By mining consistent information among multiple views and low-rank correlation information among multiple labels, and combining the contribution weight of each view with complementary information, this method can effectively handle multi-view multi-label classification problems.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Biochemical Research Methods
Hui Li, Zhaohong Deng, Haitao Yang, Xiaoyong Pan, Zhisheng Wei, Hong-Bin Shen, Kup-Sze Choi, Lei Wang, Shitong Wang, Jing Wu
Summary: This paper proposes a multi-view classification method called DMSK for the identification of circRNA-RBP interaction sites, based on multi-view deep learning, subspace learning, and multi-view classifier. The method utilizes pseudo-amino acid and pseudo-dipeptide components of circRNA sequences, predicts the secondary structure, extracts context-dependent features, and combines convolutional neural networks with long short-term memory networks to obtain deep features. The proposed method outperforms existing methods in predicting circRNA-RBP interactions.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Information Systems
Jianyu Chen, Zhongyuan Wang, Caixia Zheng, Kangli Zeng, Qin Zou, Laizhong Cui
Summary: This paper proposes a novel gait recognition framework, GaitAMR, which extracts the most discriminative subject features by holistic and partial temporal aggregation strategies. It also enhances view stability by utilizing optimal view features as supplementary information. Experimental results demonstrate that GaitAMR improves gait recognition in occlusion conditions and outperforms state-of-the-art methods.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Liang Zhao, Yanshan Xiao, Bo Liu, Zhifeng Hao
Summary: "PLL is a method for handling partial label learning, aiming to identify the ground-truth label from a set of candidate labels. Most existing PLL approaches focus on the single-view problem and do not address the multi-view problem. This paper proposes a novel multi-view paunknown method."
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Bo Liu, Weibin Li, Yanshan Xiao, Xiaodong Chen, Laiwang Liu, Changdong Liu, Kai Wang, Peng Sun
Summary: Multi-label learning is a popular topic in machine learning that deals with the simultaneous association of multiple labels with given samples. This paper proposes a new multi-view multi-label learning method called ELSMML, which considers label correlation. The method constructs a crafted label correlation matrix to describe label relationships and utilizes multi-view learning and dimension reduction to exploit latent semantic label information and feature information, building a classifier in a low dimensional space. The ELSMML model is optimized using the accelerated proximal gradient method and achieves better performance compared to other baselines according to evaluation metrics.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Zhiwen Cao, Xijiong Xie
Summary: In this paper, we propose a structure learning method called SCMvFS for multi-view feature selection. The method effectively explores the heterogeneous and homogeneous information from multiple views to improve feature selection results.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Information Systems
Hoang-Nhat Tran, Hong-Quan Nguyen, Huong-Giang Doan, Thanh-Hai Tran, Thi-Lan Le, Hai Vu
Summary: This paper presents a novel method for Human Action Recognition (HAR) under different camera viewpoints using deep learning techniques, achieving robust performance across various datasets, especially for harder classes. The proposed pc-MvDA approach constructs a common feature space to maintain view-invariant features among separated camera views, leading to consistent performance gains in experimental results.
Article
Ecology
Shanshan Xie, Jing Lu, Jiang Liu, Yan Zhang, Danjv Lv, Xu Chen, Youjie Zhao
Summary: Birds, as important members of the ecosystem, are good indicators of the ecological environment. This paper proposes a birdsong classification model that combines deep learning and machine learning by utilizing multi-view features. The experimental results show that this method achieves higher accuracy and lower dimensionality in birdsong recognition.
ECOLOGICAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Haozan Liang, Guihua Wen, Yang Hu, Mingnan Luo, Pei Yang, Yingxue Xu
Summary: Food recognition is critical in healthcare applications, but current methods face challenges due to diverse appearances and non-uniform composition of ingredients. The proposed Multi-View Attention Network incorporates multiple semantic features for comprehensive representation. Experiments show significant improvement in performance and reduced parameter size.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Artificial Intelligence
Zixi Liang, Ming Yin, Junli Gao, Yicheng He, Weitian Huang
Summary: This paper proposes a View Knowledge Transfer Network (VKTNet) for multi-view action recognition, even when some views are incomplete. The view knowledge transferring is achieved using conditional generative adversarial network (cGAN), effectively extracting high-level semantic features and bridging the semantic gap between different views. Additionally, a Siamese Scaling Network (SSN) is proposed for efficiently fusing the decision results achieved by each view.
IMAGE AND VISION COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Wei Liu, Jiazheng Yuan, Gengyu Lyu, Songhe Feng
Summary: In this paper, we propose a Label-Dependent Multi-view Multi-label method named M2LD, which incorporates label information into the feature subspace for learning a more discriminative feature subspace. Extensive experiments show that M2LD can achieve superior or comparable performance against state-of-the-art methods.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Ilyes Bendjoudi, Frederic Vanderhaegen, Denis Hamad, Fadi Dornaika
Summary: This paper proposes a new deep learning architecture for context-based multi-label multi-task emotion recognition, with a key focus on the new loss function called multi-label focal loss (MFL). Experimental results demonstrate that the combination of MFL with Huber loss performs the best, outperforming other combinations of loss functions, and excelling particularly on less frequent labels.
INFORMATION FUSION
(2021)
Article
Computer Science, Artificial Intelligence
Kaicheng Fu, Changde Du, Shengpei Wang, Huiguang He
Summary: In this article, a novel multi-view multi-label hybrid model is proposed for fine-grained emotion decoding, which can accurately predict multiple emotional states of humans and overcome the limitations of existing methods in analyzing emotional expression.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)