Huadóng Ma
YOU?
Author Swipe
View article: Constraints on dark matter boosted by supernova shock within the effective field theory framework from the CDEX-10 experiment
Constraints on dark matter boosted by supernova shock within the effective field theory framework from the CDEX-10 experiment Open
Supernova shocks can boost dark matter (DM) particles to high, yet nonrelativistic, velocities, providing a suitable mechanism for analysis within the framework of the nonrelativistic effective field theory (NREFT). These accelerated DM so…
View article: Synergistic Tensor and Pipeline Parallelism
Synergistic Tensor and Pipeline Parallelism Open
In the machine learning system, the hybrid model parallelism combining tensor parallelism (TP) and pipeline parallelism (PP) has become the dominant solution for distributed training of Large Language Models~(LLMs) and Multimodal LLMs (MLL…
View article: A Dynamic Service Offloading Algorithm Based on Lyapunov Optimization in Edge Computing
A Dynamic Service Offloading Algorithm Based on Lyapunov Optimization in Edge Computing Open
This study investigates the trade-off between system stability and offloading cost in collaborative edge computing. While collaborative offloading among multiple edge servers enhances resource utilization, existing methods often overlook t…
View article: mmHolmes: Amodal Millimeter-wave Sensing by Understanding Human Kinetics
mmHolmes: Amodal Millimeter-wave Sensing by Understanding Human Kinetics Open
Though mmWave sensing shows huge potential for recognizing human activities in an advantageous contact-less, privacy-protection manner, its performance in daily life household scenarios has not been fully understood yet. To understand the …
View article: PASS: A Novel PPG-based Aortic Stenosis Screening System
PASS: A Novel PPG-based Aortic Stenosis Screening System Open
Aortic stenosis (AS) is the most prevalent valvular heart disease, potentially leading to severe complications such as heart failure, stroke, and sudden death if left untreated. Many patients remain undiagnosed due to the absence of promin…
View article: Semi-supervised Contrastive Learning for Reliable Sleep Staging with Small Labeled Photoplethysmography Data
Semi-supervised Contrastive Learning for Reliable Sleep Staging with Small Labeled Photoplethysmography Data Open
Sleep monitoring is essential for assessing the quality of the body's rest. In medicine, it involves collecting polysomnography (PSG) data in hospitals, along with expert annotations. For convenient sleep monitoring, some studies on wearab…
View article: A Dynamic Service Offloading Algorithm Based on Lyapunov Optimization in Edge Computing
A Dynamic Service Offloading Algorithm Based on Lyapunov Optimization in Edge Computing Open
This study investigates the trade-off between system stability and offloading cost in collaborative edge computing. While collaborative offloading among multiple edge servers enhances resource utilization, existing methods often overlook t…
View article: Triassic High-Mg Diorites and Granitoids in the NE Pamir Reveal Tectonic Evolution of the Paleo-Tethys Ocean
Triassic High-Mg Diorites and Granitoids in the NE Pamir Reveal Tectonic Evolution of the Paleo-Tethys Ocean Open
The Western Kunlun-Pamir Orogen (WKPO) in the northwestern Tibetan Plateau holds crucial information on the Tethyan evolution. Until now, the subduction polarity and the assemblage processes of the Northern, Central, and Southern Pamir dur…
View article: Metallogenic conditions and prediction of the Tugeman lithium-beryllium deposit in Xinjiang: Insights from geology and Worldview-3 imagery
Metallogenic conditions and prediction of the Tugeman lithium-beryllium deposit in Xinjiang: Insights from geology and Worldview-3 imagery Open
View article: 中亚造山带东天山古生代幕式成矿过程与机理
中亚造山带东天山古生代幕式成矿过程与机理 Open
View article: Large-scale Permian-Jurassic rare-metal mineralization in the Altai Orogenic Belt: A review
Large-scale Permian-Jurassic rare-metal mineralization in the Altai Orogenic Belt: A review Open
View article: VIoTGPT: Learning to Schedule Vision Tools Towards Intelligent Video Internet of Things
VIoTGPT: Learning to Schedule Vision Tools Towards Intelligent Video Internet of Things Open
Video Internet of Things (VIoT) has shown full potential in collecting an unprecedented volume of video data. How to schedule the domain-specific perceiving models and analyze the collected videos uniformly, efficiently, and especially int…
View article: Towards Efficient Object Re-Identification with a Novel Cloud-Edge Collaborative Framework
Towards Efficient Object Re-Identification with a Novel Cloud-Edge Collaborative Framework Open
Object re-identification (ReID) is committed to searching for objects of the same identity across cameras, and its real-world deployment is gradually increasing. Current ReID methods assume that the deployed system follows the centralized …
View article: Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning Open
In this paper, we propose a new Robust Disentangled Counterfactual Learning (RDCL) approach for physical audiovisual commonsense reasoning. The task aims to infer objects' physics commonsense based on both video and audio input, with the m…
View article: Identification of pegmatite dikes based on remote sensing spectral library and WorldView-3 Data: A Case study in the central Altyn region of Xinjiang
Identification of pegmatite dikes based on remote sensing spectral library and WorldView-3 Data: A Case study in the central Altyn region of Xinjiang Open
View article: VLM-Assisted Continual learning for Visual Question Answering in Self-Driving
VLM-Assisted Continual learning for Visual Question Answering in Self-Driving Open
In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays a vital role in en…
View article: Target-driven Self-Distillation for Partial Observed Trajectories Forecasting
Target-driven Self-Distillation for Partial Observed Trajectories Forecasting Open
Accurate prediction of future trajectories of traffic agents is essential for ensuring safe autonomous driving. However, partially observed trajectories can significantly degrade the performance of even state-of-the-art models. Previous ap…
View article: Towards Robust Unsupervised Attention Prediction in Autonomous Driving
Towards Robust Unsupervised Attention Prediction in Autonomous Driving Open
Robustly predicting attention regions of interest for self-driving systems is crucial for driving safety but presents significant challenges due to the labor-intensive nature of obtaining large-scale attention labels and the domain gap bet…
View article: A New Teacher-Reviewer-Student Framework for Semi-supervised 2D Human Pose Estimation
A New Teacher-Reviewer-Student Framework for Semi-supervised 2D Human Pose Estimation Open
Conventional 2D human pose estimation methods typically require extensive labeled annotations, which are both labor-intensive and expensive. In contrast, semi-supervised 2D human pose estimation can alleviate the above problems by leveragi…
View article: Towards Balanced Continual Multi-Modal Learning in Human Pose Estimation
Towards Balanced Continual Multi-Modal Learning in Human Pose Estimation Open
3D human pose estimation (3D HPE) has emerged as a prominent research topic, particularly in the realm of RGB-based methods. However, RGB images are susceptible to limitations such as sensitivity to lighting conditions and potential user d…
View article: Human Grasp Generation for Rigid and Deformable Objects with Decomposed VQ-VAE
Human Grasp Generation for Rigid and Deformable Objects with Decomposed VQ-VAE Open
Generating realistic human grasps is crucial yet challenging for object manipulation in computer graphics and robotics. Current methods often struggle to generate detailed and realistic grasps with full finger-object interaction, as they t…
View article: Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression
Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression Open
Action Quality Assessment (AQA), which aims at automatic and fair evaluation of athletic performance, has gained increasing attention in recent years. However, athletes are often in rapid movement and the corresponding visual appearance va…
View article: Diffusion-based SDRTV-to-HDRTV Reconstruction with Artifact Suppression
Diffusion-based SDRTV-to-HDRTV Reconstruction with Artifact Suppression Open
View article: Learning Group Interactions and Semantic Intentions for Multi-Object Trajectory Prediction
Learning Group Interactions and Semantic Intentions for Multi-Object Trajectory Prediction Open
Effective modeling of group interactions and dynamic semantic intentions is crucial for forecasting behaviors like trajectories or movements. In complex scenarios like sports, agents' trajectories are influenced by group interactions and i…
View article: T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving
T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving Open
Understanding the traffic scenes and then generating high-definition (HD) maps present significant challenges in autonomous driving. In this paper, we defined a novel Traffic Topology Scene Graph, a unified scene graph explicitly modeling …
View article: Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving
Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving Open
In current open real-world autonomous driving scenarios, challenges such as sensor failure and extreme weather conditions hinder the generalization of most autonomous driving perception models to these unseen domain due to the domain shift…
View article: BP3: Improving Cuff-less Blood Pressure Monitoring Performance by Fusing mmWave Pulse Wave Sensing and Physiological Factors
BP3: Improving Cuff-less Blood Pressure Monitoring Performance by Fusing mmWave Pulse Wave Sensing and Physiological Factors Open
Cuff-less methods, especially pulse wave analysis (PWA) techniques with PPG/mmWave sensing, have shown great potential for non-intrusive blood pressure (BP) monitoring. However, the state-of-the-art solutions are only validated on small-sc…
View article: Diffusion-driven Incomplete Multimodal Learning for Air Quality Prediction
Diffusion-driven Incomplete Multimodal Learning for Air Quality Prediction Open
Predicting air quality using multimodal data is crucial to comprehensively capture the diverse factors influencing atmospheric conditions. Therefore, this study introduces a multimodal learning framework that integrates outdoor images with…
View article: Learning Exposure Correction in Dynamic Scenes
Learning Exposure Correction in Dynamic Scenes Open
Exposure correction aims to enhance visual data suffering from improper\nexposures, which can greatly improve satisfactory visual effects. However,\nprevious methods mainly focus on the image modality, and the video counterpart\nis less ex…
View article: CSAdv: Class-Specific Adversarial Patches for DETR-Style Object Detection
CSAdv: Class-Specific Adversarial Patches for DETR-Style Object Detection Open
Remarkable advancements have been made in the field of object detection, and given its widespread application, it is of paramount importance to investigate the robustness of detection models. However, previous methods have primarily focuse…