Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks229 from public data
- A framework of blockchain-based secure and privacy-preserving E-government system189
A framework of a decentralized e-government peer-to-peer (p2p) system using the blockchain technology is proposed, which can ensure both information security and privacy while simultaneously increasing the trust of the public sectors.
- Exploring spatial-frequency-sequential relationships for motor imagery classification with recurrent neural network161
A deep recurrent neural network (RNN) with a sliding window cropping strategy (SWCS) to signal classification of MI-BCIs is applied, and the proposed GRU-RNN architecture achieves the lowest misclassification rates on all BCI benchmark datasets.
- Meta Architecture for Point Cloud Analysis115
This paper takes the initiative to explore and propose a unified framework called PointMeta, to which the popular 3D point cloud analysis approaches could fit, and shows very strong performance in efficiency and effectiveness through extensive experiments on challenging benchmarks, and verifies the necessity and benefits of high-level interpretation, contrast, and comparison like PointMeta.
- DiffRate : Differentiable Compression Rate for Efficient Vision Transformers110
Differentiable Compression Rate (DiffRate), a novel token compression method that has several appealing properties prior arts do not have, is proposed and achieves state-of-the-art performance.
- Towards Compact CNNs via Collaborative Compression105
A Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models by simultaneously learning the model sparsity and low-rankness and proposes multi-step heuristic compression to remove redundant compression units step-by-step.
- 102
- AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration94
This work designs a unified search space that consists of all possible time steps and various architectures and introduces a two stage evolutionary algorithm to find the optimal solution in the designed search space.
- 82
- AffineQuant: Affine Transformation Quantization for Large Language Models72
This paper advocates for the direct optimization using equivalent Affine transformations in PTQ (AffineQuant) using the corresponding inverse matrix to ensure equivalence between the pre- and post-quantization outputs of PTQ, thereby maintaining its efficiency and generalization capabilities.
- 70
- Staged Competence Learning in Developmental Robotics70
An approach towards developmental growth for robotics that utilizes natural constraints in a general learning mechanism that is applicable to all levels of control and behavior, and can be implemented in any robotic configuration.
- Machine Learning Algorithms for Network Intrusion Detection64
This chapter systematically reviews two groups of common intrusion detection systems using fuzzy logic and artificial neural networks, and evaluates them by utilizing the widely used KDD 99 benchmark dataset.
- Low-Cost Inertial Measurement Unit Calibration With Nonlinear Scale Factors59
The errors of acceleration and angular velocity led by the algorithm are significantly smaller than those resulted from the existing approaches using the same testing data sets, demonstrating a remarkable improvement of 64.12% and 47.90%, respectively.
- 56
- 56
- 1xN Pattern for Pruning Convolutional Neural Networks54
This paper proposes a novel 1×N pruning pattern that prunes consecutive N output kernels with the same input channel index into one block, which serves as a basic pruning granularity of thisPruning pattern.
- Feature grouping and selection: A graph-based approach53
A general framework based on graph processing and three-way mutual information metrics is proposed in this paper that works by clustering similar features into groups, from which representative features are then drawn and two different feature selection techniques are presented.
- A robot calligraphy system: From simple to complex writing by human gestures51
A robot calligraphy system that firstly applies human arm gestures to establish a font database of Chinese character elementary strokes and English letters, then uses the created database and human gestures to write Chinese characters and English words.
- Self-Organizing Brain Emotional Learning Controller Network for Intelligent Control System of Mobile Robots50
The comparative study using the cutting-edge neural network-based control systems confirms that the proposed network is capable of producing better control performances with high computational efficiency.
- Use of human gestures for controlling a mobile robot via adaptive CMAC network and fuzzy logic controller44
A system which uses human gestures to control an autonomous mobile robot integrating a manipulator and a video surveillance platform, which is able to conveniently control a mobile robot using virtual driving method, with smooth manoeuvring trajectories in various speeds.
- A developmental algorithm for ocular–motor coordination44
A model of ocular-motor development, inspired by ideas and data from developmental psychology, is presented, which is simple, extremely fast, self-calibrating, adaptive to change, and exhibits emergent stages of behaviour as learning progresses.
- Training Compact CNNs for Image Classification Using Dynamic-Coded Filter Fusion41
This paper presents a novel filter pruning method, dubbed dynamic-coded filter fusion (DCFF), to derive compact CNNs in a computation-economical and regularization-free manner for efficient image classification.
- Developmental learning for autonomous robots40
Ideas and inspiration from early infant psychology are used to examine how robot systems could discover the structure of their local sensory-motor spaces and learn how to coordinate these for the control of action.
- A Secure and Privacy-Preserving E-Government Framework Using Blockchain and Artificial Immunity39
The experimental results show the efficacy of the proposed framework in that it can mitigate insider and external threats in e-Government systems whilst simultaneously preserving the privacy of information.
- Learning Efficient GANs for Image Translation via Differentiable Masks and Co-Attention Distillation38
A novel GAN compression method, termed DMAD, is introduced by proposing a Differentiable Mask and a co-attention Distillation that simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of the light-weight model.
- 38
- A Functional-link-based Fuzzy Brain Emotional Learning Network for Breast Tumor Classification and Chaotic System Synchronization38
An efficient neural network that is a generalization of several existing neural networks, such as a function link neural network, a fuzzy neural network and a brain emotional learning network is developed and applies it for both classification and control problems.
- 36
- 36
- 35
- SiMaN: Sign-to-Magnitude Network Binarization34
This article proves that the learned weights of binarized networks roughly follow a Laplacian distribution that does not allow entropy maximization, and demonstrates that the weight binarization problem can be effectively solved by simply removing the sign function.
- 33
- Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers33
This article proposes a robotic hand–eye coordination system by simulating the human behavior pattern to achieve a fast and robust reaching ability by using two neural-network-based controllers.
- Towards Big data Governance in Cybersecurity31
This paper proposes a framework of big data governance that guides organisations to make better data-informed business decisions within the related regularity framework, with close attention paid to data security, privacy, and accessibility.
- Gaze-Informed Egocentric Action Recognition for Memory Aid Systems31
A new gaze-informed feature extraction approach, by which the features are extracted from the regions around the gaze points and thus representing the genuine ROI from a first person of view, is proposed.
- A Music-Driven Dance System of Humanoid Robots30
A humanoid robot dance system driven by musical structures and emotions is developed that can generate diverse robotic dance motions, showing the novelty and diversity of robot dance.
- A developmental approach to robotic pointing via human–robot interaction30
A developmental learning approach to robotic pointing is introduced, by exploiting the interactions between a human and a robot by first applying a reinforcement learning algorithm to guide the robot to create attempt movements towards a salient object that is out of the robot's initial reachable space.
- 29
- Wavelet Fuzzy Brain Emotional Learning Control System Design for MIMO Uncertain Nonlinear Systems29
The proposed wavelet fuzzy brain emotional learning controller (WFBELC) model can be applied to obtain more satisfactory control performance and be more suitable to deal with the influence of the uncertainty of the MIMO nonlinear systems.
- Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective28
This paper first formulate the oscillation in PTQ and prove the problem is caused by the difference in module capacity, and then tries to solve this problem by introducing a principled and generalized frame-work theoretically.
- Towards sparse rule base generation for fuzzy rule interpolation28
This paper proposes a novel sparse fuzzy rule base generation method to support fuzzy rule interpolation, which first identifies important rules that cannot be accurately approximated by their neighbouring ones to initialise the rule base.
- 27
- Sundial-GAN: A Cascade Generative Adversarial Networks Framework for Deciphering Oracle Bone Inscriptions27
This paper proposes a cascade generative adversarial networks (GAN) framework for deciphering OBI characters, named "Sundial-GAN'', which is a cascaded structure to simulate Chinese characters' evolutionary process from an OBI character to its potential modern Chinese character.
- An Improved Fuzzy Brain Emotional Learning Model Network Controller for Humanoid Robots27
An improved fuzzy BEL model (iFBEL) neural network by integrating a fuzzy neural network (FNN) to a conventional BEL, in an effort to better support humanoid robots.
- Integration of an actor-critic model and generative adversarial networks for a Chinese calligraphy robot26
A roboticcalligraphy model that combines a generative adversarial network (GAN) and deep reinforcement learning to enable a calligraphy robot to learn to write Chinese character strokes directly from images captured from Chinese calligraphic textbooks is proposed.
- Dynamic QoS solution for enterprise networks using TSK fuzzy interpolation26
A dynamic QoS solution based on the differentiated services (DiffServ) approach for enterprise networks, which is able to modify the priority level of a packet in real time by adjusting the value of Differentiated Services Code Point (DSCP) in Internet Protocol (IP) header of network packets.
- Robotic Free Writing of Chinese Characters via Human–Robot Interactions25
This paper aims to demonstrate the efforts towards in-situ applicability of EMMARM, as to provide real-time information about concrete mechanical properties such as E-modulus and compressive strength.
- Bi-directional Masks for Efficient N:M Sparse Training24
A novel method of Bi-directional Masks (Bi-Mask) with its two central innovations in separate sparse masks in the two directions of forward and backward propagation to obtain training acceleration and an efficient weight row permutation method to maintain performance.
- 24
- You only compress once: Towards effective and elastic BERT compression via exploit–explore stochastic nature gradient23
A novel approach, YOCO-BERT, to achieve compress once and deploy everywhere and proposes a novel stochastic nature gradient optimization method to guide the generation of optimal candidate architecture which could keep a balanced trade-off between explorations and exploitation.
- Real-Time Image Demoireing on Mobile Devices23
A dynamic demoireing acceleration method (DDA) towards a real-time deployment on mobile devices by designing a novel moire prior that considers both colorfulness and frequency information of moire patterns and training all networks in a parameter-shared supernet paradigm to avoid additional parameter burden.
- 4-D Memristive Chaotic Systems-Based Audio Secure Communication Using Dual-Function-Link Fuzzy Brain Emotional Controller23
An efficient algorithm for the synchronization of 4-D memristive chaotic systems and their applications for audio secure communication and the results show that the proposed method can accommodate the system perturbation very well.
- 23
- GANCCRobot: Generative adversarial nets based chinese calligraphy robot23
Experimental results demonstrate that the proposed model enables a calligraphic robot to successfully write fundamental Chinese strokes based on a given type and style, with overall good quality.
- A K-means Interval Type-2 Fuzzy Neural Network for Medical Diagnosis23
The Lyapunov theory is used to verify the convergence and stability of the proposed method and the performance of the system is evaluated using several medical datasets from the University of California at Irvine.
- Histogram of Fuzzy Local Spatio-Temporal Descriptors for Video Action Recognition23
A novel method to handle uncertainty within the process of pixel voting with regard to the bins in the histogram by fuzzifying feature extractors is proposed, which better represents the ambiguous boundaries between the bins and, thus, the fuzziness of the spatio-temporal visual information entailed in videos.
- 22
- Wavelet Interval Type-2 Fuzzy Quad-Function-Link Brain Emotional Control Algorithm for the Synchronization of 3D Nonlinear Chaotic Systems22
This study provides a novel quad-function-link network to adjust the lower and upper weights of a wavelet interval type-2 fuzzy brain emotional structure to increase the response and performance for the synchronization of 3D nonlinear chaotic systems.
- Uncovering the Over-Smoothing Challenge in Image Super-Resolution: Entropy-Based Quantification and Contrastive Optimization21
This paper proposes an explicit solution to the center-oriented optimization (COO) problem, called Detail Enhanced Contrastive Loss (DECLoss), which utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution and thereby decrease the entropy.
- 21
- Fine-grained Data Distribution Alignment for Post-Training Quantization21
A fine-grained data distribution alignment (FDDA) method to boost the performance of post-training quantization on ImageNet, based on two important properties of batch normalization statistics (BNS) observed in deep layers of the trained network.
- 21
- Discriminator-Cooperated Feature Map Distillation for GAN Compression20
The irreplaceability of teacher discriminator is investigated and an inventive discriminator-cooperated distillation, abbreviated as DCD, is presented towards refining better feature maps from the generator, showing superior results compared with existing GAN compression methods.
- Effect of Different Movement Speed Modes on Human Action Observation: An EEG Study20
The discipline curves suggested that a moderate speed within a decent inter-stimulus interval (ISI) range produced the highest hMNS activations, and a new method for constructing non-invasive brain machine brain interfaces with moderate AO-BCI and motor imagery BCI was inspired by this paper.
- 19
- Lottery Jackpots Exist in Pre-Trained Models19
It is shown that high-performing and sparse sub-networks without the involvement of weight training, termed “lottery jackpots”, exist in pre-trained models with unexpanded width and a novel short restriction method is proposed to restrict change of masks that may have potential negative impacts on the training loss, which leads to a faster convergence and reduced oscillation for searching lottery jackpots.
- SMMix: Self-Motivated Image Mixing for Vision Transformers19
This work proposes an novel and effective Self-Motivated image Mixing method (SMMix), which motivates both image and label enhancement by the model under training itself, and introduces a fine-grained label assignment technique that co-trains the output tokens of mixed images with fine-grained supervision.
- Multi-scale representation of surface-enhanced Raman spectroscopy data for deep learning-based liver cancer detection19
The experimental results demonstrate that the combination of SERS, wavelet transform, and deep learning has the potential to function as a non-invasive tool for the rapid detection of liver cancer.
- Fuzzy cerebellar model articulation controller network optimization via self-adaptive global best harmony search algorithm19
This paper proposes to apply harmony search algorithm to find optimal network parameters, so as to achieve better performances of FCMAC networks, and shows that the networks optimized by SGHS perform the faster convergence speed and better accuracy.
- An Infant Development-inspired Approach to Robot Hand-eye Coordination19
A novel developmental learning approach for hand-eye coordination in an autonomous robotic system is presented, supported by an experimental evaluation, which shows that the control system is implemented simply, and that the learning approach provides fast and incremental learning of behavioural competence.
- 18
- 18
- 18
- 18
- 17
- 17
- Decoupled Sliding Mode Control of Underactuated Nonlinear Systems Using a Fuzzy Brain Emotional Cerebellar Model Control System16
A new intelligent control algorithm for the decoupling control of a class of single-input fourth-order underactuated nonlinear systems and can be applied to the practical systems if the computation time is acceptable for these practical systems.
- 16
- Autonomous Robotic Choreography Creation via Semi-interactive Evolutionary Computation16
A semi-interactive evolutionary computation method for a humanoid robot to create robotic choreography autonomously and emphasizes that the humanoid robot should develop its good dance poses and movements autonomously by means of machine learning.
- 16
- An SSVEP Recognition Method by Combining Individual Template with CCA15
ITCCA (Individual Template Canonical Correlation Analysis) optimized the reference signal by incorporating features of the subject's EEG data into the artificial reference template, and the performance of this approach was compared with that of the standard CCA.
- Job shop planning and scheduling for manufacturers with manual operations15
A new genetic algorithm-based job shop scheduling system by integrating a fuzzy learning and inference sub-system in an effort to address this limitation in improving the efficiency of manual manufacturing operations.
- Integration of classifier diversity measures for feature selection-based classifier ensemble reduction15
A new ensemble subset evaluation method that integrates classifier diversity measures into a novel classifier ensemble reduction framework that achieves relatively good performance with less computational time is proposed.
- 14
- An LSTM Based Generative Adversarial Architecture for Robotic Calligraphy Learning System14
A machine calligraphy learning system using a Long Short-Term Memory (LSTM) network and a generative adversarial network (GAN), which enables the robots to learn and generate the sequences of Chinese character stroke (i.e., writing trajectory).
- 14
- 14
- Learning Robotic Hand-eye Coordination Through a Developmental Constraint Driven Approach14
A new method for robotic hand-eye coordination by imitating the developmental progress of human infants is proposed, which employs a brain-like neural network system inspired by infant brain structure to learn hand- eye coordination, and adopts a developmental mechanism from psychology to drive the robot.
- Wavelet transform and deep learning-based obstructive sleep apnea detection from single-lead ECG signals13
An automatic sleep apnea classification model (CA-EfficientNet) based on the wavelet transform, a lightweight neural network, and a coordinated attention mechanism is proposed to address the problems of complex feature extraction, data imbalance, and low model capacity.
- 13
- Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective12
Shapley-MoE, an efficient pruning method for MoE models inspired by cooperative game theory, is proposed by quantifying each expert’s contribution via Shapley value, and two novel methods to improve sampling accuracy and efficiency are proposed.
- Curvature-based sparse rule base generation for fuzzy rule interpolation12
This paper proposes a new sparse fuzzy rule base generation method that uses curvature values to identify important rules that cannot be accurately approximated by their neighbouring ones for initialising a compact rule base.
- Electroencephalogram-based brain-computer interface for the Chinese spelling system: a survey12
A common framework unifying the current EEGCS and EEGES systems is proposed, in which the concept of EEG-based choice acts as a core component.
- 12
- 11
- A recurrent wavelet-based brain emotional learning network controller for nonlinear systems11
A novel brain emotional neural network that combines the advantages of the wavelet function, the recurrent mechanism, and the brain emotional learning system, for optimal performance on nonlinear problems under uncertain environments is proposed.
- 11
- 10
- LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal10
A novel lightweight deep neural network that processes shadow images in the LAB color space that well outperforms state-of-the-art methods and its parameters and computational costs are reduced by several orders of magnitude.
- 10
- Intelligent wavelet fuzzy brain emotional controller using dual function-link network for uncertain nonlinear control systems10
The proposed algorithm comprises a dual function-link network-based multilayer wavelet fuzzy brain emotional controller and a sign(.) functional compensator to achieve favorable control performance for uncertain nonlinear systems.
- 10
- 9
- 9
- Gradient Boost with Convolution Neural Network for Stock Forecast9
A model combining the advantages of two methods to forecast the change of stock price, CNN and GBoost is presented, which has better performance against current popular methods.
- 9
- 9
- Manual Task Completion Time Estimation for Job Shop Scheduling Using a Fuzzy Inference System9
A job completion time estimation system which estimates the completion times for different tasks under different conditions such that the intelligent scheduling system can make a schedule globally by artificially treating the assembly lines as virtual machines.
- 8
- 8
- 8
- 8
- A Unified Framework for 3D Point Cloud Visual Grounding8
This paper proposes Superpoint Mask Branch, which serves a dual purpose and eliminates the heavy computational overhead on the high-resolution visual features for upsampling, and enables 3DRefTR to achieve both well-performing 3DRES and3DREC capacities with only a 6% additional latency compared to the original 3DREC model.
- 8
- 8
- 8
- 8
- Event-Anchored Frame Selection for Effective Long-Video Understanding7
Event-Anchored Frame Selection (EFS), a hierarchical, event-aware pipeline that partitions the video stream into visually homogeneous temporal segments, which serve as proxies for semantic events and ensures the final keyframe set jointly optimizes for event coverage, query relevance, and visual diversity.
- EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs7
This work proposes an efficient and fast framework for fine-tuning sparse LLMs based on minimizing reconstruction error that achieves superior results on various benchmarks, and can be executed on a single 16GB GPU.
- 7
- 7
- 7
- 7
- Motion-Aware Caching for Efficient Autoregressive Video Generation6
MotionCache is proposed, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics and employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token.
- Multimodal Inplace Prompt Tuning for Open-set Object Detection6
This study introduces a redundancy assessment metric to identify uniform attention patterns and incorporates multimodal inplace prompt tuning (MIPT) to enrich the text prompt with visual clues in areas with high redundancy.
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- Exploring Content Relationships for Distilling Efficient GANs4
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices and designs a novel GAN compression oriented knowledge.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Searching Lightweight Neural Network for Image Signal Processing2
An automated search framework is proposed that derives ISP models with high image quality while satisfying the low-computation requirement and adopts the weight-sharing strategy by introducing a supernet and decouple the architecture search into two stages, supernet training and hard-aware evolutionary search.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action Policies–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization–
Inspired by DETR, this work proposes a unified framework, 3DGCTR, to jointly solve these two distinct but closely related tasks in an end-to-end fashion, and facilitates simultaneous multi-task training on both tasks, mutually enhancing their performance.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.