若有疑問，請聯繫公告聯絡人:

張晏瑜
國立交通大學 電腦視覺研發中心
300 新竹市大學路1001號電子資訊大樓6樓608室
TEL：(03)5712121分機59249
releccalii@gmail.com
-----------------------------------------------------------------------------------

會議名稱:APSIPA Annual Summit and Conference 2026
會議時間:2026/11/9~2026/11/12
會議網址:https://apsipa2026.org/special_sessions.html

 

Generative and Multimodal Signal Processing for Vision and Multimedia Systems

Organizers

Prof. Ching-Chun Huang - National Yang Ming Chiao Tung University, Taiwan (chingchun@nycu.edu.tw)
Assoc. Prof. Yu-Lun Liu - National Yang Ming Chiao Tung University, Taiwan (yulunliu@cs.nycu.edu.tw)
Assoc. Prof. Manh-Hung Nguyen - University of Technology and Engineering, Vietnam (hungnm@hcmute.vn)

Introduction

Recent advances in generative modeling and multimodal learning are reshaping signal processing for vision and
multimedia systems. Modern pipelines integrate images, video, audio, text, depth, and 3D/4D sensor signals (e.g., LiDAR/IMU/radar) to enable robust perception, restoration, understanding, and content generation under real-world constraints such as noise, blur, compression, low-light, missing modalities, and domain shifts. While diffusion models, transformers, flow-based models, and implicit neural representations have advanced controllable synthesis and inverse problems, key challenges remain in reliability, efficiency, interpretability, and deployment.

This special session aims to bring together researchers in signal processing, computer vision, and multimedia to explore generative and multimodal signal processing. We encourage contributions grounded in signal-processing principles (e.g., priors, sampling, spectral/time-frequency analysis, compression, uncertainty modeling, and efficiency) and end-to-end multimodal system design for real-world applications.

Important Dates

Submission of Full Papers: April 24, 2026

Notification of Paper Acceptance: June 1, 2026

Camera-Ready Paper Submission: June 15, 2026