Kun-Yu Lin

8

Papers

30

Total Citations

Papers (8)

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

ViSpeak: Visual Instruction Feedback in Streaming Videos

Person De-reidentification: A Variation-guided Identity Shift Modeling

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks

ParGo: Bridging Vision-Language with Partial and Global Views

Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks

Less Static, More Private: Towards Transferable Privacy-Preserving Action Recognition by Generative Decoupled Learning