Publications

@inproceedings{1997-Gardner-PASAD,

title = {Prosody Analysis for Speaker Affect Determination},

author = {A. Gardner and I. Essa},

year  = {1997},

date = {1997-10-01},

booktitle = {Workshop on Perceptual User Interfaces (PUI)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1997-Essa-CPFCE,

title = {Computational Perception in Future Computing Environments},

author = {Irfan Essa and Gregory Abowd and Chris Atkeson},

url = {https://www.cc.gatech.edu/fce/pubs/pui97-fce.html},

year  = {1997},

date = {1997-01-01},

urldate = {1997-01-01},

booktitle = {Workshop on Perceptual User Interfaces (PUI)},

keywords = {aging-in-place, computational health, intelligent environments},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1996-Basu-MRMHT,

title = {Motion Regularization for Model-based Head Tracking},

author = {Sumit Basu and Irfan Essa and Alex Pentland},

url = {https://ieeexplore.ieee.org/document/547019},

doi = {10.1109/ICPR.1996.547019},

isbn = {0-8186-7282-X},

year  = {1996},

date = {1996-10-01},

urldate = {1996-10-01},

booktitle = {Proceedings of International Conference on Pattern Recognition (ICPR)},

abstract = {This paper describes a method for the robust tracking of rigid head motion from video. This method uses a 3D ellipsoidal model of the head and interprets the optical flow in terms of the possible rigid motions of the model. This method is robust to large angular and translational motions of the head and is not subject to the singularities of a 2D model. The method has been successfully applied to heads with a variety of shapes, hair styles, etc. This method also has the advantage of accurately capturing the 3D motion parameters of the head. This accuracy is shown through comparison with a ground truth synthetic sequence (a rendered 3D animation of a model head). In addition, the ellipsoidal model is robust to small variations in the initial fit, enabling the automation of the model initialization. Lastly, due to its consideration of the entire 3D aspect of the head, the tracking is very stable over a large number of frames. This robustness extends even to sequences with very low frame rates and noisy camera images.

},

keywords = {computer vision, face & gesture, ICPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1996-Essa-MTIAFHUIFV,

title = {Modeling, Tracking and Interactive Animation of Faces and Heads using Input from Video},

author = {Irfan Essa and Sumit Basu and Trevor Darrell and Alex Pentland},

url = {https://ieeexplore.ieee.org/abstract/document/540489},

doi = {10.1109/CA.1996.540489},

isbn = {0-8186-7588-8},

year  = {1996},

date = {1996-06-01},

urldate = {1996-06-01},

booktitle = {Computer Animation Conference},

pages = {68--79},

publisher = {IEEE Computer Society Press},

abstract = {We describe tools that use measurements from video for the extraction of facial modeling and animation parameters, head tracking, and real time interactive facial animation. These tools share common goals but rely on varying details of physical and geometric modeling and in their input measurement system. Accurate facial modeling involves fine details of geometry and muscle coarticulation. By coupling pixel by pixel measurements of surface motion to a physically based face model and a muscle control model, we have been able to obtain detailed spatio temporal records of both the displacement of each point on the facial surface and the muscle control required to produce the observed facial motion. We discuss the importance of this visually extracted representation in terms of realistic facial motion synthesis. A similar method that uses an ellipsoidal model of the head coupled with detailed estimates of visual …

},

keywords = {computer vision, face & gesture},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1995-Brand-CAVGU,

title = {Causal Analysis for Visual Gesture Understanding},

author = {M. Brand and I. Essa},

year  = {1995},

date = {1995-10-01},

booktitle = {AAAI Fall Symposium on Computational Models for Integrating Language and Vision},

abstract = {We are exploring the use of high-level knowledge about bodies in the visual understanding of gesture. Our hypothesis is that many gestures are metaphorically derived from the motor programs of our everyday interactions with objects and people. For example, many dismissive gestures look like an imaginary object is being brushed or tossed away. At the discourse level, this implicit mass represents a referent in the conversation; at the scene-formation level, the dismissive gesture obeys many of the kinematic and dynamic constraints that would shape an actual tossing. Thus this metaphor provides us with constraints for both discourse annotation and visual processing. In this paper we present some preliminary results interpreting complex gesture sequences in video.},

keywords = {gesture recognition},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1995-Darrell-AEGAIE,

title = {Attention-driven Expression and Gesture Analysis in an Interactive Environment},

author = {T. Darrell and I. Essa and A. Pentland},

year  = {1995},

date = {1995-01-01},

booktitle = {Proceedings of International Workshop on Automatic Face and Gesture Recogntion (FG)},

pages = {135--140},

publisher = {Editor, M. Bichsel},

address = {Zurich, Switzerland},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1995-Essa-FERUDMME,

title = {Facial Expression Recognition using a Dynamic Model and Motion Energy},

author = {I. Essa and A. Pentland},

year  = {1995},

date = {1995-01-01},

booktitle = {IEEE International Conference on Computer Vision (ICCV)},

pages = {360--367},

publisher = {IEEE Computer Society},

address = {Cambridge, MA},

keywords = {computer vision, ICCV},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1994-Darrell-CINREA,

title = {Correlation and Interpolation Networks for Real-Time Expression Analysis/Synthesis},

author = {T. Darrell and I. Essa and A. Pentland},

editor = {G. Tesauro and D. S. Touretzky and T. K. Leen},

url = {https://papers.nips.cc/paper/999-correlation-and-interpolation-networks-for-real-time-expression-analysissynthesis},

year  = {1994},

date = {1994-12-01},

booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},

volume = {7},

publisher = {MIT Press},

abstract = {We describe a framework for real-time tracking of facial expressions 

that uses neurally-inspired correlation and interpolation methods. A 

distributed view-based representation is used to characterize facial state, 

and is computed using a replicated correlation network. The ensemble 

response of the set of view correlation scores is input to a network based 

interpolation method, which maps perceptual state to motor control states 

for a simulated 3-D face model. Activation levels of the motor state 

correspond to muscle activations in an anatomically derived model. By 

integrating fast and robust 2-D processing with 3-D models, we obtain a 

system that is able to quickly track and interpret complex facial motions 

in real-time.},

keywords = {face & gesture, face processing, gesture recognition},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1994-Essa-VSOEFAP,

title = {A Vision System for Observing and Extracting Facial Action Parameters},

author = {I. Essa and A. Pentland},

url = {https://ieeexplore.ieee.org/document/323813},

doi = {10.1109/CVPR.1994.323813},

year  = {1994},

date = {1994-01-01},

urldate = {1994-01-01},

booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

pages = {76--83},

publisher = {IEEE Computer Society},

abstract = {We describe a computer vision system for observing the "action units" of a face using video sequences as input. The visual observation (sensing) is achieved by using an optimal estimation optical flow method coupled with a geometric and a physical (muscle) model describing the facial structure. This modeling results in a time-varying spatial patterning of facial shape and a parametric representation of the independent muscle action groups, responsible for the observed facial motions. These muscle action patterns may then be used for analysis, interpretation, and synthesis. Thus, by interpreting facial motions within a physics-based optimal estimation framework, a new control model of facial movement is developed. The newly extracted action units (which we name "FACS+") are both physics and geometry-based, and extend the well-known FACS parameters for facial expressions by adding temporal information and non-local spatial patterning of facial motion.< >

},

keywords = {computer vision, CVPR, face & gesture, face processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1994-Essa-TFM,

title = {Tracking Facial Motion},

author = {I. Essa and T. Darrell and A. Pentland},

year  = {1994},

date = {1994-01-01},

booktitle = {Proceedings of IEEE Workshop on Motion of Nonrigid and Articulated Objects},

pages = {36--42},

publisher = {IEEE Computer Society},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1994-Pentland-VGA,

title = {Visually guided animation},

author = {Alex Pentland and Trevor Darrell and Irfan Essa and Ali Azarbayejani and Stan Sclaroff},

year  = {1994},

date = {1994-01-01},

urldate = {1994-01-01},

booktitle = {Computer Animation Conference},

pages = {76 - 83},

publisher = {IEEE Computer Society Press},

organization = {IEEE Computer Society},

keywords = {computer animation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1994-Pentland-VGIA,

title = {Visually guided interaction and animation},

author = {Alex Pentland and Stan Sclaroff and Trevor Darrell and Irfan Essa and Ali Azarbayejani and Thad Starner},

year  = {1994},

date = {1994-01-01},

urldate = {1994-01-01},

booktitle = {Asilomar Conference on Signals, Systems, and Computers},

volume = {2},

pages = {1287 - 1291},

address = {Pacific Grove, CA},

keywords = {computer animation, human-computer interaction, multimodal interfaces},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1992-Sclaroff-VMAUAPGMGA,

title = {Vision-based Modeling: An application of a Unified Approach for Physical and Geometric Modeling for Graphics and Animation},

author = {S. Sclaroff and I. Essa and A. Pentland},

year  = {1992},

date = {1992-01-01},

booktitle = {Proceedings of Eurographics Workshop on Animations and Simulations},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}