Call for Papers
The Third Facial Micro-Expressions Grand Challenge (MEGC): New Learning Methods for Spotting and Recognition
Download Call for Papers (pdf version).
Micro-facial expressions (MEs) are involuntary movements of the face that occur spontaneously when a person experiences an emotion but attempts to suppress or repress the facial expression, most likely in a high-stakes environment. As such, the duration of MEs is very short with the general duration of not more than 500 milliseconds (ms), and is the telltale sign that distinguishes them from a normal facial expression. Computational analysis and automation of tasks on micro expressions is an emerging area in face research, with a strong interest appearing as recent as 2014. Only recently, the availability of a few spontaneously induced facial micro-expression datasets has provided the impetus to advance further from the computational aspect. There are two facial macro- and micro- expression databases which contain long videos: the CAS(ME)2 with 98 sequences at 30 fps and the SAMM Long Videos dataset with 147 sequences at 200 fps. While much research has been done on short videos, there has been not many attempts to spot micro-expressions on long videos. This workshop is organized with the aim of promoting interactions between researchers and scholars from within this niche area of research, and also those from broader, general areas of computer vision and psychology research.
This workshop has two main agendas:
- To organize the Third Grand Challenge for facial micro-expression research: spotting macro and micro expressions on long videos.
- To solicit original works that address a variety of challenges of ME research, but not
- ME spotting/detection by using self-supervised learning
- ME recognition by using self-supervised learning
- ME feature representation and computational analysis
- Unified ME spot-and-recognize schemes
- Deep learning techniques for MEs spotting and recognition
- MEs data analysis and synthesis
- New datasets for MEs
- Psychology of MEs