The TC9 on Pattern Recognition in Human-Machine-Interaction is one of the Technical Committees of the International Association for Pattern Recognition (IAPR). TC 9 was approved by the IAPR ExCo at ICPR 2016.

Human-machine interaction (HMI) typically takes place on a rather crude explicit question-answer level, whereas human-human interaction is multifaceted, and is consisting of manifold interactive feedback loops between interlocutors, comprising social components (e.g. display rules, social state), moods, feelings, personal goals, nonverbal and paralinguistic conversation channels and even more. In order to close this gap, it is crucial for a machine to perceive and understand the user’s current interaction and affective state, as well as it is necessary to register the user’s social signals, which are composed of dynamic multimodal behavioral cues. Building intelligent artificial agents or companions capable to interact with humans in the same way humans interact with each other is a major challenge in HMI. The TC9 on Pattern Recognition in Human-Machine-Interaction mainly focuses on pattern recognition, machine learning and information fusion methods for the perception of the user’s affective state, activities and intentions.

Research topics of  TC 9  include but are not limited:

Pattern Recognition and Machine Learning Algorithms to recognize emotions, activities and intentions

  • Learning from unlabeled and partially labeled data
  • Learning with noisy labels
  • Deep learning architectures
  • Learning of time series

Algorithms to combine information from multiple modalities

  • Information fusion (early, late, intermediate fusion)
  • Multi Classifier Systems and Multi View Classifiers
  • Temporal information fusion
  • Dealing with Uncertainty

Applications of HMI

  • Intelligent interaction
  • Assistive systems
  • Companion systems
  • Robotics

Datasets and benchmarks relevant for HMI research