Computer Vision Modeling
The projects I did before: face anti-spoofing, crowd counting, re-identification, transformer, remote sensing, image enahancement, image super-resolution, imagenet classification, image retrival, medical imaging.
About Me – Haoran Duan is a PhD student in the Perception(VIViD) Lab, at Durham University. He is an enthusiastic researcher in DeepLearning or MachineLearning applications/theories and he is also a data scientist. He did lots of deep learning-based engineering projects (e.g., computer vision, time series) in his early career, while now he is focusing on discoverings of the rationale and the future development of artificial intelligence with help of deep learning and big data. He believes the future AI will be data-centric and human-centric. Nice to meet you 🙂
The projects I did before: face anti-spoofing, crowd counting, re-identification, transformer, remote sensing, image enahancement, image super-resolution, imagenet classification, image retrival, medical imaging.
This is my project of sensor-based time-series modeling
Efficient Architecture Search for Speaker Recognition in the Wild
This is the page related to the Data-Centric projects I did or I am doing or I am collaborating. Most of them are focusing on three aspects: Zero-Shot Learning, Semi-Supervised Learning, and Unsupervised Learning.
ODE/PDE/SDE
3D, Point Cloud, Mesh, Urban Level Monitoring/Forcasting/Planing
Loughborough University
The collection of zero-shot learning papers
Our Paper is under-review now, stay tuned.
Our Paper is under-review now, stay tuned.