Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Yu-Wei Zhan et al.
Summary: This paper introduces a novel cross-modal online hashing method DOCH, which utilizes discrete latent factor model and label embedding to generate high-quality hash codes, discretely learns hash codes through an optimization algorithm, and experimental results on two real-world datasets demonstrate its superiority.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Xin Liu et al.
Summary: The study introduces a fast discriminative discrete hashing method, using orthogonal rotation of semantic data and introducing orthogonal basis and epsilon-dragging technique to maximize the discriminative power of semantic information. Additionally, an orthogonal transformation scheme is proposed to ensure consistency between data features and semantic representation, improving retrieval performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Mingbao Lin et al.
Summary: In this paper, a novel supervised online hashing scheme called FCOH is proposed to address the adaptivity and efficiency issues in online image hashing. By introducing a novel and efficient inner product operation, FCOH achieves fast online adaptivity and efficiency through class-wise updating and semi-relaxation optimization.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Runmin Wang et al.
Summary: NrDCMH is an end-to-end solution for handling multi-modal data, improving cross-modal hashing through noise instance detection and hash code learning. Experimental results show that NrDCMH performs significantly better with noisy label annotations and achieves competitive results in 'noise-free' scenarios.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Weiwei Wang et al.
Summary: This paper discusses learning-based image hashing techniques and proposes a self-supervised hashing method based on sparse graph, which effectively solves problems in unsupervised hashing methods, achieving superior performance through iterative optimization.
INFORMATION SCIENCES
(2021)
Article
Automation & Control Systems
Xi Yang et al.
Summary: The study introduces a hierarchical deep embedding (HDE) model that utilizes contextual evidence and an improved polar meshing scheme to achieve significant improvements in aurora image retrieval.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Computer Science, Artificial Intelligence
Chao Zhang et al.
Summary: This article explores the generalization performance of multitask learning (MTL) by viewing it as a learning process of vector-valued functions (VFs) and answers two theoretical questions regarding when MTL outperforms single-task learning (STL) and when it guarantees task consistency during learning. By introducing VFs, the article is able to examine task behavior and relatedness in MTL, deriving deviation and symmetrization inequalities to provide a generalization bound for MTL. The findings highlight the impact of synergic relatedness between task groups on MTL performance and present a sufficient condition for task consistency in MTL.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Xiushan Nie et al.
Summary: The study proposed a deep multiscale fusion hashing (DMFH) method for cross-modal retrieval, which designs different network branches and adopts multiscale fusion models to embed multiscale semantics into final hash codes, making them more representative. The DMFH can learn common hash codes directly without relaxation, avoiding accuracy loss during hash learning, and experimental results on three benchmark datasets demonstrate its relative superiority.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoshuang Shi et al.
Summary: By introducing a novel alternative optimization mechanism to linearize the quartic problem, a scalable symmetric discrete hashing algorithm is proposed to gradually and smoothly update each batch of binary codes. The method also includes a greedy symmetric discrete hashing algorithm to update each bit of batch binary codes for further smoothness. The optimization mechanism can be extended to solve non-convex optimization problems in various pairwise based hashing algorithms, showing superior performance in similarity and ranking order retrieval tasks compared to recent methods.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Mingbao Lin et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Computer Science, Artificial Intelligence
Zechao Li et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Computer Science, Artificial Intelligence
Cheng Deng et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Computer Science, Information Systems
Yiming Shen et al.
INFORMATION SCIENCES
(2020)
Article
Computer Science, Artificial Intelligence
Mingbao Lin et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Artificial Intelligence
De Xie et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Artificial Intelligence
Zechao Li et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2019)
Article
Automation & Control Systems
Wing W. Y. Ng et al.
IEEE TRANSACTIONS ON CYBERNETICS
(2019)
Article
Computer Science, Artificial Intelligence
Tao Yao et al.
PATTERN RECOGNITION
(2019)
Article
Computer Science, Artificial Intelligence
Cheng Deng et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Long-Kai Huang et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2018)
Article
Computer Science, Artificial Intelligence
Fatih Cakir et al.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2017)
Article
Computer Science, Information Systems
Ke Wang et al.
INFORMATION SCIENCES
(2016)
