A5040230389- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Traffic Prediction and Management Techniques
- Computer Graphics and Visualization Techniques
- Asthma and respiratory diseases
- Robotics and Sensor-Based Localization
- Human Pose and Action Recognition
- X-ray Diffraction in Crystallography
- 3D Shape Modeling and Analysis
- Traffic control and management
- Allergic Rhinitis and Sensitization
- Air Quality and Health Impacts
- Crystallization and Solubility Studies
- Dermatology and Skin Diseases
- Infrastructure Maintenance and Monitoring
- Climate Change and Health Impacts
- Autonomous Vehicle Technology and Safety
- Urban and spatial planning
- Physical Activity and Health
- Time Series Analysis and Forecasting
- Children's Physical and Motor Development
- Remote Sensing and Land Use
- Multimodal Machine Learning Applications
- Behavioral Health and Interventions
- Pregnancy and Medication Impact
Chengdu University of Traditional Chinese Medicine
2023-2025
Tsinghua University
2024
Alibaba Group (United States)
2024
Zhejiang University
2022-2024
Beijing University of Civil Engineering and Architecture
2024
Recent advances in implicit neural representations and differentiable rendering make it possible to simultaneously recover the geometry materials of an object from multi-view RGB images captured under unknown static illumination. Despite promising results achieved, indirect illumination is rarely modeled previous methods, as requires expensive recursive path tracing which makes inverse computationally intractable. In this paper, we propose a novel approach efficiently recovering...
This paper aims to tackle the challenge of dynamic view synthesis from multi-view videos. The key observation is that while previous grid-based methods offer consistent rendering, they fall short in capturing appearance details a complex scene, domain where image-based rendering demonstrate opposite properties. To combine best two worlds, we introduce Im4D, hybrid scene representation consists geometry and representation. Specifically, encoded as 4D density function composed spatiotemporal...
<title>Abstract</title> Background Smoking exposure is a leading cause of asthma. This study used the Global Burden Disease (GBD) database (1990–2021) to analyze global, regional, and national burden asthma induced by smoking in middle-aged older adults. Methods Data on deaths, Disability-Adjusted Life Years (DALYs), Age-Standardized Death Rate (ASDR), Mortality (ASMR) from were extracted. Multiple figures created illustrate smoking-related The Bayesian Age-Period-Cohort (BAPC) model...
This paper presents an approach that reconstructs a hand-held object from monocular video. In contrast to many recent methods directly predict geometry by trained network, the proposed does not require any learned prior about and is able recover more accurate detailed geometry. The key idea hand motion naturally provides multiple views of can be reliably estimated pose tracker. Then, recovered solving multi-view reconstruction problem. We devise implicit neural representation-based method...
We present a novel method for local image feature matching. Instead of performing detection, description, and matching sequentially, we propose to first establish pixel-wise dense matches at coarse level later refine the good fine level. In contrast methods that use cost volume search correspondences, self cross attention layers in Transformer obtain descriptors are conditioned on both images. The global receptive field provided by enables our produce low-texture areas, where detectors...
We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers from low efficiency. revisit its design choices derive multiple improvements both efficiency accuracy. One key observation is that performing the transformer over entire feature map redundant due to shared local information, therefore we propose an...
Indirect photolysis driven by photochemically produced reactive intermediates (PPRIs) is pivotal for the transformations and fates of pollutants in nature. While well-studied bulk water, indirect processes at environmental interfaces remain largely unexplored. This study reveals a significant acceleration photodegradation organic soil-water interface wetlands. Organic experienced ubiquitously enhanced interfaces, with rates 1.41 ± 0.01 to 4.27 0.03-fold higher than those water. enhancement...
To evaluated the risk ratio of Allergic rhinitis (AR) people on symptoms after COVID-19 infection, and explored relationship between AR infection. An observational study was performed from outpatient department Hospital Chengdu University Chinese Medicine. Participants completed an electronic survey January 10 to 20, 2023. We divided participants into three groups according disease information population: non-AR group (AR-N), patients with sublingual immunotherapy (AR-S), conventional...
Predicting traffic flows is crucial for management. Due to the complex and interconnected nature of road networks, in an area influenced not only by temporal historical traffic, but also spatial patterns neighboring areas. This paper presents a hybrid methodology that incorporates spectral spatial-temporal correlation analysis each segment uses boosting model prediction (SST-Boost). Spectral utilized decompose flow data into periodic trends volatility components, relevance matrix introduced...
为了解我国小学的幼小衔接现状和热点，本文通过高级检索主题和关键词“幼小衔接”“小学语文”“教学策略”，运用CiteSpace 软件对CNKI（2014—2024）收录的270 篇我国幼小衔接背景下小学语文教学研究文献进行了统计与计量，通过关键词共现、突现分析和聚类分析，进一步对该领域的研究现状进行了基于知识图谱的可视化分析，根据分析结果提出了研究趋势：聚焦衔接主体，以儿童为本；联合实施主体，形成衔接合力；注重跨学科融合，拓展研究维度，以期为幼小衔接研究提供有价值的参考。
We propose a new method named OnePose for object pose estimation. Unlike existing instance-level or category-level methods, does not rely on CAD models and can handle objects in arbitrary categories without instance- category-specific network training. draws the idea from visual localization only requires simple RGB video scan of to build sparse SfM model object. Then, this is registered query images with generic feature matching network. To mitigate slow runtime we graph attention that...