Yan Shu (舒言)

I'm an incoming PhD candidate at the University of Trento. I will join MHUG Group supervised by Paolo Rota and Nicu Sebe .

Previously, I was a research intern in Beijing Academy of Artificial Intelligence (BAAI) supervised by Bo Zhao and Zheng Liu .

Before that, I got Master`s degree from Harbin Institute of Technology, supervised by Shaohui Liu. I also worked as research assistant in Institute of Information Engineering, Chinese Academy of Sciences, advised by Yu Zhou

Email  /  Scholar  /  Twitter  /  Github  /  小红书

Research

I'm interested in computer vision, multimodal learning, video understanding and OCR. Below are some selected publications. (* indicates equal contribution.)

First-ever hour-scale video understanding models.

First-ever comprehensive long video benchmark.

A diffusion-based scene text editing model as well as a real-world scene text editing benchmark.

A diffusion-based scene text generation model as well as a synthetic scene text detection dataset.

Video quality assessment framework based on CLIP.

Survey on low-level scene text processing methods.

A model designed for ambiguous scene text detection.

Education and Working Experience

Services