A5091619690- Urban Heat Island Mitigation
- Land Use and Ecosystem Services
- Urban Green Space and Health
- Eurasian Exchange Networks
- Multimodal Machine Learning Applications
- Chinese history and philosophy
- Indian and Buddhist Studies
- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Remote Sensing and LiDAR Applications
- 3D Shape Modeling and Analysis
- Human Pose and Action Recognition
- Advanced Image and Video Retrieval Techniques
- Noise Effects and Management
- Soviet and Russian History
- 3D Surveying and Cultural Heritage
- Advanced Neural Network Applications
- Flood Risk Assessment and Management
- Landslides and related hazards
- Acute Ischemic Stroke Management
- Visual Attention and Saliency Detection
- Stroke Rehabilitation and Recovery
- Religious Studies and Spiritual Practices
- Cryospheric studies and observations
- Musculoskeletal pain and rehabilitation
Chinese Academy of Sciences
2020-2024
Research Center for Eco-Environmental Sciences
2024
Xidian University
2023
Institute of Geographic Sciences and Natural Resources Research
2020-2023
University of Chinese Academy of Sciences
2020-2023
Arizona State University
2023
Tianjin University
2022
The exacerbated thermal environment in cities, with the urban heat island (UHI) effect as a prominent example, has been source of many adverse environmental issues, including increase health risks, degradation air quality and ecosystem services, reduced resiliency engineering infrastructure. Last decades have witnessed tremendous efforts resources being invested to find sustainable solutions for mitigation, whereas relative contributions different UHI attributes their patterns...
Deep learning techniques have led to remarkable breakthroughs in the field of object detection and spawned a lot scene-understanding tasks recent years. Scene graph has been focus research because its powerful semantic representation applications scene understanding. Graph Generation (SGG) refers task automatically mapping an image or video into structural graph, which requires correct labeling detected objects their relationships. In this paper, comprehensive survey achievements is...
3D scene graph prediction is important for intelligent agents to gather information and perceive semantics of their environments. However, constructing an effective nontrivial given the complexity natural scenes. Existing solutions representation scenes still distinguish each detailed discrepancy among all relationships as flat thinking, ignoring mechanism used by humans perform this task. Inspired role prefrontal cortex in hierarchical reasoning, we analyze problem from a novel perspective:...
Geological disasters not only hinder the ecological security guarantee in urban agglomerations, but also pose serious threat to life and property of residents areas. The study establishes a "hazard-vulnerability-exposure" three-dimensional risk assessment model, adopts an information value model assess hazard, use landscape indices analyze vulnerability nighttime light data indicate population exposure, then quantitatively assesses watershed-scale risks geological their patterns. results...
In-depth understanding of a 3D scene not only involves locating/recognizing individual objects, but also requires to infer the relationships and interactions among them. However, since scenes contain partially scanned objects with physical connections, dense placement, changing sizes, wide variety challenging relationships, existing methods perform quite poorly limited training samples. In this work, we find that inherently hierarchical structures space in aid automatic association semantic...
3D object detection is a fundamental task in scene understanding. Numerous research efforts have been dedicated to better incorporate Hough voting into the pipeline. However, due noisy, cluttered, and partial nature of real scans, existing voting-based methods often receive votes from surfaces individual objects together with severe noises, leading sub-optimal performance. In this work, we focus on distributional properties point clouds formulate process as generating new points high-density...
Deep learning techniques have led to remarkable breakthroughs in the field of generic object detection and spawned a lot scene-understanding tasks recent years. Scene graph has been focus research because its powerful semantic representation applications scene understanding. Graph Generation (SGG) refers task automatically mapping an image into structural graph, which requires correct labeling detected objects their relationships. Although this is challenging task, community proposed SGG...
This project aims to accelerate the upper limb rehabilitation speed for hemiplegia and disability caused by stroke other diseases designs an arm-assisted exoskeleton robot. According standard size of human limb, 3D model robot was designed in SolidWorks, DH parameters kinematics equations were derived. By studying arm posture movement, state data each joint movement analyzed. It carried out MATLAB simulate structure manipulator, analyze motion trajectory planning, verify rationality robot's...