Changyin Sun
YOU?
Author Swipe
View article: Integrating experiential learning theory with innovation and entrepreneurship education: a qualitative study on Chinese medical students
Integrating experiential learning theory with innovation and entrepreneurship education: a qualitative study on Chinese medical students Open
Background Traditional medical education models emphasizing didactic knowledge transmission inadequately prepare healthcare professionals for complex challenges in modern medicine. Innovation and Entrepreneurship Education (IEE) offers opp…
View article: NN-based fast finite-time fault-tolerant control for second-order multi-agent systems with dynamic event-triggered strategy
NN-based fast finite-time fault-tolerant control for second-order multi-agent systems with dynamic event-triggered strategy Open
View article: The function of PCSK9 in doxorubicin-induced cardiotoxicity and its underlying mechanism
The function of PCSK9 in doxorubicin-induced cardiotoxicity and its underlying mechanism Open
View article: Multi-level noise reduction for 2D backlighting x-ray radiography using Frequency Residual U-Net
Multi-level noise reduction for 2D backlighting x-ray radiography using Frequency Residual U-Net Open
X-ray backlighting is a crucial diagnostic technique in inertial confinement fusion (ICF) experiments, enabling the observation of the geometrical structure of an imploding capsule. However, x-ray emission from a short-pulse laser illumina…
View article: EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation
EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation Open
Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take a…
View article: Attention-Based Multi-Objective Control for Morphing Aircraft
Attention-Based Multi-Objective Control for Morphing Aircraft Open
This paper proposes a learning-based joint morphing and flight control framework for avian-inspired morphing aircraft. Firstly, a novel multi-objective multi-phase optimal control problem is formulated to synthesize the comprehensive fligh…
View article: AI protocol for retrieving protein dynamic structures from two-dimensional infrared spectra
AI protocol for retrieving protein dynamic structures from two-dimensional infrared spectra Open
Understanding the dynamic evolution of protein structures is crucial for uncovering their biological functions. Yet, real-time prediction of these dynamic structures remains a significant challenge. Two-dimensional infrared (2DIR) spectros…
View article: A Novel Adaptive Enhanced Nonsingular Fast Terminal Sliding Mode Control for Collaborative Robots
A Novel Adaptive Enhanced Nonsingular Fast Terminal Sliding Mode Control for Collaborative Robots Open
View article: Masked Vision-and-Language Pre-Training for Scene Graph Generation
Masked Vision-and-Language Pre-Training for Scene Graph Generation Open
View article: Monitoring C–C coupling in catalytic reactions via machine-learned infrared spectroscopy
Monitoring C–C coupling in catalytic reactions via machine-learned infrared spectroscopy Open
Tracking atomic structural evolution along chemical transformation pathways is essential for optimizing chemical transitions and enhancing control. However, molecule-level knowledge of structural rearrangements during chemical processes re…
View article: ISLU: Indexing-Efficient Sparse LU Factorization for Circuit Simulation on GPUs
ISLU: Indexing-Efficient Sparse LU Factorization for Circuit Simulation on GPUs Open
View article: Correction to: Aperiodically intermittent event-triggered control for practical fixed-time consensus under denial-of-service attack
Correction to: Aperiodically intermittent event-triggered control for practical fixed-time consensus under denial-of-service attack Open
View article: Window-to-Window BEV Representation Learning for Limited FoV Cross-View Geo-localization
Window-to-Window BEV Representation Learning for Limited FoV Cross-View Geo-localization Open
Cross-view geo-localization confronts significant challenges due to large perspective changes, especially when the ground-view query image has a limited field of view with unknown orientation. To bridge the cross-view domain gap, we for th…
View article: LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition
LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition Open
Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into r…
View article: Single Image Super-Resolution Based on Global-Local Information Synergy
Single Image Super-Resolution Based on Global-Local Information Synergy Open
Although several image super-resolution solutions exist, they still face many challenges. CNN-based algorithms, despite the reduction in computational complexity, still need to improve their accuracy. While Transformer-based algorithms hav…
View article: MCMS: Multi-Category Information and Multi-Scale Stripe Attention for Blind Motion Deblurring
MCMS: Multi-Category Information and Multi-Scale Stripe Attention for Blind Motion Deblurring Open
Deep learning-based motion deblurring techniques have advanced significantly in recent years. This class of techniques, however, does not carefully examine the inherent flaws in blurry images. For instance, low edge and structural informat…
View article: Empowering Large Language Models on Robotic Manipulation with Affordance Prompting
Empowering Large Language Models on Robotic Manipulation with Affordance Prompting Open
While large language models (LLMs) are successful in completing various language processing tasks, they easily fail to interact with the physical world by generating control sequences properly. We find that the main reason is that LLMs are…
View article: Inside back cover
Inside back cover Open
View article: Point-to-Spike Residual Learning for Energy-Efficient 3D Point Cloud Classification
Point-to-Spike Residual Learning for Energy-Efficient 3D Point Cloud Classification Open
Spiking neural networks (SNNs) have revolutionized neural learning and are making remarkable strides in image analysis and robot control tasks with ultra-low power consumption advantages. Inspired by this success, we investigate the applic…
View article: ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation
ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation Open
Data augmentation plays a crucial role in improving the data efficiency of reinforcement learning (RL). However, the generation of high-quality augmented data remains a significant challenge. To overcome this, we introduce ACAMDA (Adversar…
View article: Temporal Correlation Vision Transformer for Video Person Re-Identification
Temporal Correlation Vision Transformer for Video Person Re-Identification Open
Video Person Re-Identification (Re-ID) is a task of retrieving persons from multi-camera surveillance systems. Despite the progress made in leveraging spatio-temporal information in videos, occlusion in dense crowds still hinders further p…
View article: Artificial Intelligence-based Amide-II Infrared Spectroscopy Simulation for Monitoring Protein Hydrogen Bonding Dynamics
Artificial Intelligence-based Amide-II Infrared Spectroscopy Simulation for Monitoring Protein Hydrogen Bonding Dynamics Open
The structurally sensitive amide II infrared (IR) bands of proteins provide valuable information about the hydrogen bonding of protein secondary structures, which is crucial for understanding protein dynamics and associated functions. Howe…
View article: Fixed-Time Consensus-Based Nash Equilibrium Seeking
Fixed-Time Consensus-Based Nash Equilibrium Seeking Open
This letter examines the fixed-time stability of the Nash equilibrium (NE) in non-cooperative games.We propose a consensus-based NE seeking algorithm for situations where players do not have perfect information and communicate via a topolo…
View article: Flywheel Energy Storage System Controlled Using Tube-Based Deep Koopman Model Predictive Control for Wind Power Smoothing
Flywheel Energy Storage System Controlled Using Tube-Based Deep Koopman Model Predictive Control for Wind Power Smoothing Open
View article: XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library Open
In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe offers a wide range of functionalities, including over 40 cla…
View article: Correction: Hierarchical reinforcement learning for kinematic control tasks with parameterized action spaces
Correction: Hierarchical reinforcement learning for kinematic control tasks with parameterized action spaces Open
View article: DGMem: Learning Visual Navigation Policy without Any Labels by Dynamic Graph Memory
DGMem: Learning Visual Navigation Policy without Any Labels by Dynamic Graph Memory Open
In recent years, learning-based approaches have demonstrated significant promise in addressing intricate navigation tasks. Traditional methods for training deep neural network navigation policies rely on meticulously designed reward functi…
View article: Robust Navigation with Cross-Modal Fusion and Knowledge Transfer
Robust Navigation with Cross-Modal Fusion and Knowledge Transfer Open
Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of applications. We consider the problem of improving the gener…
View article: Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill
Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill Open
Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomot…
View article: Gastric polyp detection module based on improved attentional feature fusion
Gastric polyp detection module based on improved attentional feature fusion Open