Prospective Students

I am actively recruiting undergraduate, master, and Ph.D. students to join M³ Lab at NYCU. Our research focuses on advancing multimedia, multimodal perception, and machine learning techniques to enhance, understand, and generate intelligent media content.
If you are interested in joining our group, please check out this [introductory slide] and fill out the appropriate Google Form below:

• [Undergraduate Application Form]

• [MS/PhD Student Application Form]

• [RA/Visitor Application Form]

Research Interests

My research focuses on image and video processing, computer vision, and deep learning, with particular emphasis on perceptual quality assessment and enhancement for interactive and generative media. I aim to design methodologies that address both traditional and emerging challenges in multimedia applications.

Situated at the intersection of human perception, multimedia signal processing, and AI-driven quality modeling, my work spans applications across interactive, immersive, and generative media environments.

• Multimodal Perception and Learning
  Multimodal deep learning, cross-modal video quality assessment, and self-supervised or contrastive learning for multimodal perception. Fusion of visual, auditory, and depth modalities for enhanced media understanding.

• AI-Generated Media
  VQA for AI-generated content (GANs, diffusion models), super-resolution and enhancement for media, quality control for generative content, and aesthetic assessment and style transfer evaluation.

• Image and Video Processing / Computer Vision
  Medical image processing and analysis, image enhancement, image restoration, image segmentation, image registration, face recognition, video quality assessment (VQA), and perceptaul quality enhancement.

• Deep Learning
  Convolutional Neural Networks (CNNs), Transformers, Large Language Models (LLMs), Transfer Learning, Generative Models, and Diffusion Models.

• Interactive and Immersive Media
  Mobile cloud gaming, human avatars, virtual reality (VR) and extended reality (XR), immersive media, facial expression similarity, immersive content, and omnidirectional (360-degree) videos.

News

• Aug 2025 🎊 Paper Accepted by IEEE TIP: HoloQA: Full Reference Video Quality Assessor of Rendered Human Avatars in Virtual Reality

• Mar 2025 🎊 Paper Accepted by SIGGRAPH Conference Papers ’25 (August 10–14, 2025, Vancouver, BC, Canada): FaceExpressions-70k: A Dataset of Perceived Expression Differences

• Dec 2024 🎤 Seminar at NTU: Delivered research presentations to master's students in EE and CSIE. [Slides]

• Sep 2024 🎊 Paper Accepted by IEEE TIP: Subjective and Objective Quality Assessment of Rendered Human Avatar Videos in Virtual Reality

• Mar 2024 🎤 Talk: Delivered a presentation on my research as part of the ECE Outstanding Student Lecture Series for prospective PhD students. [Certificate] [Slides]

• Jun 2023 🎤 Talk: Delivered a presentation on Video Quality Assessment for Cloud Gaming at the VQEG Meeting.

• Jun 2023 🎊 Paper Accepted by IEEE TIP: Study of Subjective and Objective Quality Assessment of Mobile Cloud Gaming Videos

• Mar 2023 🎊 Paper Accepted by IEEE SPL: GAMIVAL: Video Quality Prediction on Mobile Cloud Gaming Content