human computer intelligent interaction
play

Human Computer Intelligent Interaction Thomas S. Huang Department - PowerPoint PPT Presentation

Human Computer Intelligent Interaction Thomas S. Huang Department of Electrical and Computer Engineering Coordinated Science Laboratory Beckman Institute for Advanced Science and Technology Center for Advanced Study University of Illinois at


  1. Human Computer Intelligent Interaction Thomas S. Huang Department of Electrical and Computer Engineering Coordinated Science Laboratory Beckman Institute for Advanced Science and Technology Center for Advanced Study University of Illinois at Urbana-Champaign

  2. Four broad research areas 1. Biometrics 2. Video event detection and recognition 3. Human computer interaction 4. Web-scale multimedia processing and applications

  3. Human Computer Interaction Multimodal Processing Display; Engine Avatar Sensors Physical Human Environment Memory Robotics Multimodal Interface Computer Human Studies: Perception, Cognition, Behavior

  4. Examples: Human to Computer  Hand tracking and applications to manipulating virtual objects, etc.  Shrug detection  Soft Biometrics: Recognition of gender, age group, emotion  Audio-visual speech recognition

  5. Example: Computer to Human  Audio-Visual emotive avatar

  6. Mona Lisa was a white female, 43 year old, 83% happy

  7. Images Data: Video Range 3D Face Model Geometry Texture Motion Analysis (tracking) Synthesis (animation)  Lip reading  Text- and Speech- driven talking face  Emotion recognition

  8. Facial Movement Action units ~10 Muscles Control points ~100 Smoothness Mesh vertices ~1000

  9. Comparison of bimodal ASR and acoustic ASR recognition performances

  10. Future: Biometrics Recognizing gender, age group, emotion/ affect from non-frontal faces and body/ movement

  11. Future: Robust Real-Time Algorithms Sensors: High-speed cameras; 3D cameras; multiple cameras Parallel computing architectures Clever algorithms

  12. Future: Applications Finding applications to fit algorithm performance: Human in the loop Multimodality Forgiving

  13. Demonstrations By Zhen Li  Gender and age group recognition By Vuong Le  3D face model from 2D face  Audio-visual emotive avatar (driven by text and emotion markers)  3D face tracking and emotion recognition

  14. Li Le Show

Recommend


More recommend