Second Workshop on Spontaneous Facial Behavior Analysis in conjunction with ACCV 2016, Taipei, November 20, 2016

  1. The Program is now available.
  2. The papers accepted by SFBA2 has been annouced to the authors.
  3. New paper submission is now close, supported by CMT (
  4. SFBA2 website open
OverviewFaces are not only one of the most cogent, naturally pre-eminent means used by human beings for the recognition of a person, but also for communicating emotions and intentions and in regulating interactions with the environment and other individuals in the vicinity. Humans are good at recognizing regular facial expressions which present a rich source of affective information. However, many spontaneous expressions, such as micro-expressions which are very rapid and subtle involuntary facial expressions, which occur when an emotion is of lower intensity, are much harder to read. Moreover, changing facial expressions in long-term interactions is a natural and powerful way of conveying personal intention, expressing emotion and regulating interpersonal communication. Automatic recognition of expressions and estimation of the intensity is thus an important step in enhancing the capability of human-computer interfaces. Furthermore, numerous studies in psychology suggest that it is facial expressions and micro-expression components (a.k.a. facial action units (AUs), facial muscle actions responsible for producing facial expressions as defined in Facial Action Coding System (FACS)) rather than holistic facial expressions that are of importance. Even though the roles of AUs in facial expressions have been studied for many years by psychologists, how to automatically detect and code the facial action units is new in the computer vision field..

Topics include, but are not limited to,

·         Expression and micro-expression databases: collection and annotation
·         Micro-expression detection, recognition and understanding
·         Action units detection for expression and micro-expression analysis
·         Intensity estimation for continuous expression analysis
·         Multimodality emotion understanding,
·         Deep learning in expression and micro-expression analysis