A5002603350- Advanced Vision and Imaging
- Multimodal Machine Learning Applications
- Advanced Image and Video Retrieval Techniques
- Computer Graphics and Visualization Techniques
- 3D Shape Modeling and Analysis
- Optical measurement and interference techniques
- Graphene and Nanomaterials Applications
- Mycobacterium research and diagnosis
- Advanced Optical Sensing Technologies
- Nanoparticle-Based Drug Delivery
- Nanoplatforms for cancer theranostics
- Image Retrieval and Classification Techniques
- Optical Systems and Laser Technology
- CCD and CMOS Imaging Sensors
- Cancer Mechanisms and Therapy
- Histone Deacetylase Inhibitors Research
- Domain Adaptation and Few-Shot Learning
- Quinazolinone synthesis and applications
- Image Processing Techniques and Applications
- Particle Accelerators and Free-Electron Lasers
Central South University
2024
Cornell University
2024
Wuhan University
2022
Chinese Academy of Sciences
2022
Shanghai Institute of Applied Physics
2022
Abstract Molecular engineering of drug delivering platforms to provide collaborative biological effects with loaded drugs is great medical significance. Herein, cannabinoid receptor 1 (CB1)‐ and reactive oxygen species (ROS)‐targeting electrosprayed microspheres (MSs) are fabricated by loading the CB1 agonist arachidonoyl 2′‐chloroethylamide (ACEA) producing ROS in a photoresponsive manner. The synergistic anti‐tumor ACEA released from MSs assessed. inhibits epidermal growth factor signaling...
In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion and 3D Gaussian representations, enabling accurate efficient scene reconstruction. particular, our technique enables high-quality reconstruction from Large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the to be modeled smaller number of images. Our approach introduces novel method for modeling complex distortions using hybrid network combines invertible...
We present a physics-based inverse rendering method that learns the illumination, geometry, and materials of scene from posed multi-view RGB images. To model illumination scene, existing works either completely ignore indirect or it by coarse approximations, leading to sub-optimal material prediction scene. In this work, we propose first locates surface points through an efficient refined sphere tracing algorithm, then explicitly traces incoming lights at each point based on reflection....
As far as Scene Graph Generation (SGG), coarse and fine predicates mix in the dataset due to crowd-sourced labeling, long-tail problem is also pronounced. Given this tricky situation, many existing SGG methods treat equally learn model under supervision of mixed-granularity one stage, leading relatively predictions. In order alleviate negative impact suboptimum annotation effect problems, paper proposes a novel Hierarchical Memory Learning (HML) framework from simple complex, which similar...
We present a physics-based inverse rendering method that learns the illumination, geometry, and materials of scene from posed multi-view RGB images. To model illumination scene, existing works either completely ignore indirect or it by coarse approximations, leading to sub-optimal material prediction scene. In this work, we propose first locates surface points through an efficient refined sphere tracing algorithm, then explicitly traces incoming lights at each point based on reflection....