Recently, machine learning is affecting the lives of people from moment to moment. These techniques have been proven and widely used in several domains. Multimedia has emerged as one key area for the application of machine learning techniques, which involves special considerations, the data is typically of very high dimension. Due to the widespread practicability, there are several important aspects to apply various machine learning on multimedia, such as over-fitting/under-fitting, regularization, interpretability, supervised/unsupervised methods, and handling of missing data. The International Workshop on Machine Learning on Multimedia Applications (MLMA 2027) will serve as a forum for researchers and technologists to discuss the state-of-the-art, exchange their experiences, present their contributions and original ideas, and set future directions in in all aspects of machine learning and technologies on multimedia applications.
Organization Committee
Program Committee Co-chairs
Yi-Cheng Chen, National Central University, Taiwan
Yan Liu, Hong Kong Polytechnic University, Hong Kong
Ying-Nong Chen, Tamkang University, Taiwan
Sheng-Chih Chen, National ChengChi University, Taiwan
Program Committee Members
Ying-Nong Chen, Tamkang University, Taiwan
Jiannong Cao, Hong Kong Polytechnic University, Hong Kong
Vincent S. Tseng, National Yang Ming Chiao Tung University, Taiwan
Keith Chan, Hong Kong Polytechnic University, Hong Kong
Jui-Hung Kao, Shih Hsin University, Taiwan
Zhenyao Liu, Taizhou University, China
Wang-Chien Lee, Pennsylvania State University, USA
Xiaohua Tony Hu, Drexel University, USA
Yu Yu, Yen, Shih Hsin University, Taiwan
Wei-Shinn Ku, Auburn University, USA
Dai Bing Tian, Singapore Management University, Singapore
Workshop Scope
The topics of interest related to this workshop include, but are not limited to:
Learning algorithm on multimedia
- Unsupervised learning
- Supervised learning
Dimensionality reduction
- Principal Component Analysis
- Independent Component Analysis
- Self-Organizing Maps
- Multi-Dimensional Scaling
Deep learning technology work structure
- Model optimization
- Learning rate tuning
Data processing
- Data Collection
- Data Cleaning
- Big data
Problem on implementation
Applications
- Social Network, Recommendation System
- Mobility, Sensor Network
- Bioinformatics
- E-Commerce