Kun-Yu Lin

I am now a post-doctoral research fellow at the University of Hong Kong, under the supervision of Prof. Kai Han. I earned my PhD degree from Sun Yat-sen University, under the supervision of Prof. Wei-Shi Zheng. Before that, I received my Bachelor's degree and Master's degree from Sun Yat-Sen University. During my PhD, I was fortunate to have the opportunity to study as a visiting student at MMLab@NTU, under the supervision of Prof. Chen Change Loy and Prof. Henghui Ding. My research interests include computer vision and machine learning.

Email  /  Scholar  /  Github

News

Selected Works

Most of my research works are about video understanding, trustworthy deep learning, and vision-language models. Some works are highlighted. # denotes equal contributions. * denotes corresponding author.

A novel vision-language task, named panoptic captioning, leading to comprehensive text representations to seek the conceptual minimum text equivalence of images.

A strong referring video object segmentation model based on visual grounding foundations. The core of the runner-up solution for the PVUW Challenge RVOS Track at CVPR 2025.

A cross-task manipulation generalization benchmark to evaluate existing Vision-Language-Action (VLA) models, and a novel generalizable VLA method.

A new paradigm, utilizing paired human-robot videos, to adapt human-data pretrained models for robotic manipulation.

A general unlearning solution for any class-centric tasks, without using any retained data and any pretrained model knowledge.

A novel connector for bridging vision and language modalities by leveraging both global and partial views, and a large-scale image-text datasets consisting of detailed captions.

The first benchmark, named XOV-Action, for the cross-domain open-vocabulary action recognition task, and a simple yet effective method to address the scene bias for the task.

A human-centric video network to address the context bias in domain adaptive action recognition.

A diversity-aware video network to address domain-specific bias in video domain generalization.

A new event-guided paradigm to address the semantic gap between observed states and unobserved actions for procedure planning in instructional videos.

An asymmetric adaptation paradigm for few-shot domain adaptive object detection.

A new vision transformer architecture for efficient and effective visual understanding.

A theorectical method to balancing in-distribution generalization and out-of-distribution detection.

A theorectical method based on implicit generators to improve out-of-distribution detection.

A simple yet effective method based on cycle transformation to filter out outlier classes in partial domain adaptation.

Services

This website borrows from Jon Barron.