Hao Chen

GF7S: A large-scale GaoFen-7 stereo dataset and self-supervised adaptation of FoundationStereo for high-resolution DSM generation

Yinxia Cao, Fenzhen Su, Dongjie Fu, Wenzhou Wu et autres

Accurate inversion of high-resolution digital surface models (DSMs) is crucial for urban science and environmental monitoring. Fully supervised deep learning has been widely adopted for DSM generation from stereo satellite imagery, but its dependence on costly ground-truth labels limits scalability in label-scarce …

cn (code pays fourni par la source)

Effect of Annealing Time on Microstructure Evolution and Mechanical Properties of Thixo-Extruded CuSn10P1 Alloy Bushings

Chengxin Li, Hao Chen, Yang Tao, Han Xiao

cn (code pays fourni par la source)

Microplastic Contamination across Interconnected Seagrass Meadows and Coral Reefs: Divergent Patterns and Limited Convergence

Hao Chen, Weilin Chen, Danni Jiang, Ronghui Zheng et autres

To address knowledge gaps in microplastic (MP) fates within connected ecosystems, this study analyzes divergence and convergence across interconnected seagrass and coral habitats. Convergence was limited: Only 16% of MP categories were shared (notably black fibrous PET), and high-density MPs consistently accumulated …

us, Rwanda, kr, Éthiopie, cn (code pays fourni par la source)

A hierarchical adaptive navigation planner for UAVs in 3D complex environments based on deep reinforcement learning

Shuyuan Liu, Yu Zhang, Guanxiong Li, Hao Chen et autres

cn (code pays fourni par la source)

Open-CD: A Comprehensive Toolbox for Change Detection

Kaiyu Li, Jiawei Jiang, Chengxi Han, Yupeng Deng et autres

We present Open-CD, a change detection toolbox that contains a rich set of change detection methods as well as related components and modules. The toolbox started from a series of open source general vision task tools, including OpenMMLab Toolkits, PyTorch Image Models …

cn, us (code pays fourni par la source)

Botnet Traffic Detection via Deep Neural Networks with Multi-Category Feature Fusion and Multi-Head Self-Attention Mechanism

Dongwei Fu, Hao Chen, Qiang He, Zhaoxin Zhang et autres

With the continuous evolution of botnet attack techniques, traditional detection methods based on signature matching and single-feature analysis are increasingly inadequate in handling complex and dynamic network threats, resulting in limited accuracy and robustness. Effectively integrating heterogeneous features from multiple sources to …

cn (code pays fourni par la source)

Tensor nested ring embedding used for domain adaptation of cross-source heterogeneous remote sensing feature tensors

Tong Gao, Min Liu, Wei Hu, Hao Chen

Multisource remote-sensing data present richer information with various resolutions, angles, and physical attributes, while their heterogeneous data structures and diverse feature distributions bring significant challenges to the existing recognition methods. Although domain adaptation methods can reduce cross-source feature differences, they can only …

cn, in (code pays fourni par la source)

Insights into Particle Size Degradation and Structural Evolution of Native-State Coke Extracted Above the Tuyere Centerline in a Large-Scale Blast Furnace

Jingbo Chen, Shengfu Zhang, Hao Chen, Hua Zhang et autres

cn (code pays fourni par la source)

Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution

Siwei Tu, Ben Fei, Weidong Yang, Fenghua Ling et autres

Accurate acquisition of surface meteorological conditions at arbitrary locations holds significant importance for weather forecasting and climate simulation. Meteorological states derived from satellite observations are often provided in the form of low-resolution grid fields. If spatial interpolation is applied directly to obtain …

cn (code pays fourni par la source)

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation

Hongxiang Zhang, Hao Chen, Muhao Chen, Tianyi Zhang

Recent decoding methods improve the factuality of large language models (LLMs) by refining how the next token is selected during generation. These methods typically operate at the token level, leveraging internal representations to suppress superficial patterns. Nevertheless, LLMs remain prone to hallucinations, …

Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction

Sijie Zhao, Feng Liu, Yiqing Guo, Pengfeng Xiao et autres

The proliferation of multi-source remote sensing data has propelled the development of deep learning for dense prediction, yet significant challenges in data and task unification persist. Current deep learning architectures for remote sensing are fundamentally rigid. They are engineered for fixed input-output …

Towards Loss-Resilient Image Coding for Unstable Satellite Networks

Hongwei Sha, Muchen Dong, Ming‐De Lu, Hao Chen et autres

Geostationary Earth Orbit (GEO) satellite communication demonstrates significant advantages in emergency short burst data services. However, unstable satellite networks, particularly those with frequent packet loss, present a severe challenge to accurate image transmission. To address it, we propose a loss-resilient image coding …

cn (code pays fourni par la source)