IEEE Trans. Cybernetics 2018
204 papers
The 2018 edition of IEEE Transactions on Cybernetics comprised 61 papers focusing on computer vision, machine learning, and control systems. A primary research theme involved video analysis and human-computer interaction, specifically modeling goal-directed human gaze patterns and temporal dynamics. Research in this area included the development of SG-FCN for video saliency detection and methods for maintaining temporal consistency through recurrent spatial attention.
In the domains of optimization and machine learning, the journal featured studies on hierarchical training for representation learning, fast large-scale spectral clustering, and multiobjective evolutionary algorithms. Technical developments also addressed efficiency, such as accelerating convolutional neural networks by removing interspatial and interkernel redundancies. Control systems research remained a core component, with papers investigating remote nonlinear state estimation and distributed formation-containment control for multiple Euler–Lagrange systems. Prolific contributors during this year included authors such as Jianmin Jiang, Hongjiu Yang, and Changyin Sun, whose work contributed to the year's emphasis on spatiotemporal representations and complex system dynamics.
Top Research Directions
Research directions most represented by IEEE Trans. Cybernetics 2018 papers.
Top Authors
Impactful Papers
Papers from IEEE Trans. Cybernetics 2018 that shaped research clusters.
Foundational
Generalized Multi-View Embedding for Visual Recognition and Cross-Modal Retrieval
foundational
Robust Learning from Incomplete Multi-Vi
Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition
foundational
Pose-Guided Spatial Attention for Human-
Influential
Tooth-Marked Tongue Recognition Using Multiple Instance Learning and CNN Features
influential
Why Depth Matters for Hierarchical Featu
Learning Domain-Invariant Subspace Using Domain Features and Independence Maximization
influential
Test Time Adaptation for Distribution Sh
Learning Domain-Invariant Subspace Using Domain Features and Independence Maximization
influential
Feature Space Augmentation for Domain Ad
SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detection
influential
Separating Foreground Motion from Stocha
Papers
« prev Page 5/5