Unsupervised Domain Adaptation Semantic Segmentation of Remote Sensing Images With Mask Enhancement and Balanced Sampling

Unsupervised Domain Adaptation Semantic Segmentation of Remote Sensing Images With Mask Enhancement and Balanced Sampling

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (一区)(IF: 7.5)

作者:2022级研究生邱元博

摘要:Unsupervised domain adaptation (UDA) aims to improve model performance in the target domain by leveraging labeled data from the source domain while not requiring labeled data in the target domain. It ... 展开

HF-T2CR:High-Fidelity Thin and Thick Cloud Removal in Optical Satellite Images through SAR Fusion

HF-T2CR:High-Fidelity Thin and Thick Cloud Removal in Optical Satellite Images through SAR Fusion

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (一区)(IF: 7.5)

作者:2021级研究生赵晓飞

摘要:Cloud removal can effectively address cloud contam- ination in optical remote sensing images. But the simultaneous removal of both thin and thick clouds remains a significant challenge due to their di... 展开

SemID: Blind Image Inpainting with Semantic Inconsistency Detection

SemID: Blind Image Inpainting with Semantic Inconsistency Detection

Tsinghua Science and Technology (一区)(IF: 6.6)

作者:2020级研究生王志宽

摘要:Most existing image inpainting methods aim to fill in the missing content in the inside-hole region of the target image. However, the areas to be restored in realistically degraded images are unspecif... 展开

Cold-start visualization recommendation driven by large language models for ocean data analysis

Cold-start visualization recommendation driven by large language models for ocean data analysis

Frontiers in Marine Science(二区)

作者:2022级研究生刘雯

摘要:Marine data is typically large-scale and complex, requiring effective visualization recommendation systems for data filtering and value extraction. The primary challenge in visualization automatic rec... 展开

Semi-Template Retrosynthesis Prediction with 3D Spatial Structures and Reaction Center Disconnection Rules

Semi-Template Retrosynthesis Prediction with 3D Spatial Structures and Reaction Center Disconnection Rules

2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者:2022级研究生魏子帅

摘要:Retrosynthesis constructs rational synthetic pathways by predicting reactants from the target product. Previous research utilizing Graph Neural Networks often relies on two-dimensional molecular repre... 展开

LCMorph: Exploiting Frequency Cues and Morphological Perception for Low-Contrast Road Extraction in Remote Sensing Images

LCMorph: Exploiting Frequency Cues and Morphological Perception for Low-Contrast Road Extraction in Remote Sensing Images

Remote Sensing (二区)(IF: 4.2)

作者:2022级研究生杨述敏

摘要:Road extraction in remote sensing images is crucial for urban planning, traffic navigation, and mapping. However, certain lighting conditions and compositional materials often cause roads to exhibit c... 展开

 ASTMEN: an adaptive spatiotemporal and multi-element fusion network for ocean surface currents forecasting

ASTMEN: an adaptive spatiotemporal and multi-element fusion network for ocean surface currents forecasting

Frontiers in Marine Science (二区)(IF: 3.7)

作者:2021级研究生王富胜

摘要: Accurate forecasting of ocean surface currents is crucial for the planning of marine activities, including fisheries, shipping, and pollution control. Previous studies have often neglected the consid... 展开

Collision-free Parking Recommendation Based on Multi-agent Reinforcement Learning in Vehicular Crowdsensing

Collision-free Parking Recommendation Based on Multi-agent Reinforcement Learning in Vehicular Crowdsensing

Digital Communications and Networks (二区)(IF: 7.5)

作者:2021级研究生类兴华

摘要:The recent proliferation of fifth-generation (5G) networks and sixth-generation (6G) networks has given rise to vehicular crowd sensing (VCS) systems which solve parking collisions by effectively ince... 展开

Differentiable Double Clustering with Edge-aware Superpixel Fitting for Unsupervised Image Segmentation

Differentiable Double Clustering with Edge-aware Superpixel Fitting for Unsupervised Image Segmentation

Displays (二区)(IF: 3.7)

作者:2020级研究生陈晓莹

摘要:Unsupervised image segmentation is an essential topic in the field of computer vision, which broke the limitation of training data and expanded application scenarios. Off-the-shelf clustering methods ... 展开

A High-Precision Interpretable Framework for Marine Dissolved Oxygen Concentration Inversion

A High-Precision Interpretable Framework for Marine Dissolved Oxygen Concentration Inversion

Frontiers in Marine Science (二区)(IF: 2.8)

作者:2022级研究生刘镇毅

摘要:Variations in Marine Dissolved Oxygen Concentrations (MDOC) play a critical role in the study of marine ecosystems and global climate evolution. Although artificial intelligence methods, represented b... 展开

FCCText: frequency-color complementary bistream structure for scene text detection

FCCText: frequency-color complementary bistream structure for scene text detection

Journal of Electronic Imaging (四区)(IF: 1)

作者:2022级研究生韩睿毅

摘要:Current scene text detection methods mainly employ RGB domain information for text localization, and their performance has not been fully exploited in many challenging scenes. Considering that the RGB... 展开

Human-like Cognition: Visual Features Grouping for Hard-to-group Text Dataset

Human-like Cognition: Visual Features Grouping for Hard-to-group Text Dataset

Journal of Electronic Imaging (四区)(IF: 1)

作者:2020级研究生刘航源

摘要:Most existing arbitrary shape text detection methods employ connected components and text center lines for grouping text instances, which assume that texts in adjacent positions belong to the same ins... 展开