Active vision
Hierarchical mixtures of experts and the EM algorithm
Neural Computation
Neural networks for pattern recognition
Neural networks for pattern recognition
Maximum conditional likelihood via bound maximization and the CEM algorithm
Proceedings of the 1998 conference on Advances in neural information processing systems II
LAFTER: Lips and Face Real-Time Tracker
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Learning and Recognizing Human Dynamics in Video Sequences
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
The Acquisition and Use of Interaction Behavior Models
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Real-Time Self-Calibrating Stereo Person Tracking Using 3-D Shape Estimation from Blob Features
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
Conjoint probabilistic subband modeling
Conjoint probabilistic subband modeling
State Space Construction for Behavior Acquisition in Multi Agent Environments with Vision and Action
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Recognition and Interpretation of Parametric Gesture
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Mixtures of Eigenfeatures for Real-Time Structure from Texture
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
A Mixed-State Condensation Tracker with Automatic Model-Switching
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
The ALIVE system: wireless, full-body interaction with autonomous agents
Multimedia Systems - Special issue on multimedia and multisensory virtual worlds
Learning Intrinsic Video Content Using Levenshtein Distance in Graph Partitioning
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
A Hidden Markov Model-Based Approach to Sequential Data Clustering
Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Designing the Minimal Structure of Hidden Markov Model by Bisimulation
EMMCVPR '01 Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Visually Mediated Interaction Using Learnt Gestures and Camera Control
GW '01 Revised Papers from the International Gesture Workshop on Gesture and Sign Languages in Human-Computer Interaction
A biologically motivated system for unconstrained online learning of visual objects
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Unsupervised discovery of structure in activity data using multiple eigenspaces
LoCA'06 Proceedings of the Second international conference on Location- and Context-Awareness
Towards computer understanding of human interactions
MLMI'04 Proceedings of the First international conference on Machine Learning for Multimodal Interaction
Authoring rules for bodily interaction: from example clips to continuous motions
IVA'12 Proceedings of the 12th international conference on Intelligent Virtual Agents
Hi-index | 0.00 |
We propose Action-Reaction Learning as an approach for analyzing and synthesizing human behaviour. This paradigm uncovers causal mappings between past and future events or between an action and its reaction by observing time sequences. We apply this method to analyze human interaction and to subsequently synthesize human behaviour. Using a time series of perceptual measurements, a system automatically discovers correlations between past gestures from one human participant (action) and a subsequent gesture (reaction) from another participant. A probabilistic model is trained from data of the human interaction using a novel estimation technique, Conditional Expectation Maximization (CEM). The estimation uses general bounding and maximization to monotonically find the maximum conditional likelihood solution. The learning system drives a graphical interactive character which probabilistically predicts a likely response to a user's behaviour and performs it interactively. Thus, after analyzing human interaction in a pair of participants, the system is able to replace one of them and interact with a single remaining user.