Haoran Tang

Fine-scale mapping of built-environment carbon emissions: A multi-source data fusion and explainable machine learning framework for high-density urban regions

Ge Shi, Haoran Tang, Wei Wang, Chuang Chen et autres

cn, us (code pays fourni par la source)

Automating Tree Crown Delineation in UAV Orthomosaics Without Annotation: An Annotation-Free Framework Coupling DeepForest, Segment Anything, and Unsupervised Clustering

Ge Shi, Haoran Tang, Wei Wang, Chuang Chen et autres

Individual-tree-level information on crown distribution and morphology underpins forest inventory, biomass estimation, and carbon accounting. High-resolution Unmanned Aerial Vehicle (UAV) imagery resolves single-tree detail, but automated crown extraction remains difficult: fully supervised segmentation depends on costly pixel-level annotation that generalizes poorly, while …

cn, us (code pays fourni par la source)

Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos Reviewed on OpenReview: https://openreview.net/forum?id=Oe5TdpPv1b

Meng Cao, Haoran Tang, Haoze Zhao, Mingfei Han et autres

FedKG: Federated POI recommendation via generative knowledge distillation against spatial heterogeneity

Lin Zhong, Jun Zeng, Ziwei Wang, Haoran Tang et autres

cn, hk (code pays fourni par la source)

AGSRec: Mitigating popularity bias via attraction-aware graph and semantic enhancement for POI recommendations

Bo Liu, Jun Zeng, Haoran Tang, Junhao Wen et autres

cn, hk (code pays fourni par la source)

Research on Centralized Frequency-Distributed Voltage Coordinated Control Strategy for Islanded Renewable Energy Delivery via Flexible HVDC System

Chunhua Li, Yijing Chen, Renqi Su, Peng Cheng et autres

For the topological structure of offshore wind power transmission via MMC with passive transmission end and large power grid at receiving end, the system operation characteristics under AC faults at the transmission and receiving ends are theoretically analyzed. Based on the AC …

cn (code pays fourni par la source)

FedHGS: A Federated Point-of-Interest Recommendation Method Based on Heterogeneous Graph Semantics

Jun Zeng, Lin Zhong, Haoran Tang, Junhao Wen et autres

Federated point-of-interest (POI) recommendation achieves global model training and optimization through a distributed training framework, ensuring that user data is always stored locally on the client side, thereby effectively protecting user data privacy. However, this distributed nature of data also severely limits …

cn, hk (code pays fourni par la source)

Multimodal Medical Image Fusion With UNet ‐Based Multi‐Scale Transformer Networks

Qingwu Fu, Jian Zhou, Jiao Du, Kai Lin et autres

ABSTRACT Multimodal medical image fusion can generate medical images that contain both functional metabolic information and structural tissue details, thereby providing doctors with more comprehensive information. Current deep learning‐based methods often employ convolutional neural networks (CNNs) for feature extraction. However, CNNs exhibit …

cn (code pays fourni par la source)

RGB-D image-based real-time pose estimation algorithm for mobile robots with rectangular body

Haoran Tang, Xiaofei Zhou, Zhimin Han, Qiang Lv

Abstract In this study, we introduce a real-time pose estimation for a class of mobile robots with rectangular body (e.g., the common automatic guided vehicles), by integrating odometry and RGB-D images. First, a lightweight object detection model is designed based on the …

cn (code pays fourni par la source)

DyBooster: Leveraging large language model as booster for dynamic recommendation

Haoran Tang, Xueyao Sun, Shiqing Wu, Zhihong Cui et autres

hk, mo, no, au (code pays fourni par la source)

DMSDRec: Dynamic Structure-Aware Graph Masked Autoencoder and Spatiotemporal Diffusion for Next-POI Recommendation

Jun Zeng, Haoran Tang, Junhao Wen, Min Gao et autres

The rise of smart devices has accelerated location-based services, creating vast trajectory data for Point-of-Interest (POI) recommendations. However, user omissions or privacy concerns often result in incomplete trajectory data, compromising sequential patterns and spatiotemporal relationships. Existing solutions using graph structures, self-supervised learning …

cn, hk (code pays fourni par la source)

Educating Language Models as Promoters: Multi-Aspect Instruction Alignment With Self-Augmentation

Xueyao Sun, Kaize Shi, Haoran Tang, Dingxian Wang et autres

E-commerce content generation necessitates creating engaging and customer-centric material to endorse products and enhance user satisfaction. Existing methods depend on task-specific feature design, which requires a fine-tailored model for each task with complex data collection and pre-processing, and their generation capabilities are …

hk, au (code pays fourni par la source)