Publications

@inproceedings{2005-Huang-TMOTO,

title = {Tracking Multiple Objects Through Occlusions},

author = {Y. Huang and I. Essa},

year  = {2005},

date = {2005-06-01},

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

pages = {1051--1058},

publisher = {IEEE Computer Society},

address = {San Diego, CA, USA},

keywords = {activity recognition, computational video, computer vision, CVPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2004-Yin-ABSR,

title = {Asymmetrically Boosted HMM for Speech Reading},

author = {P. Yin and I. Essa and J. M. Rehg},

year  = {2004},

date = {2004-06-01},

urldate = {2004-06-01},

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

pages = {pp II755-761},

publisher = {IEEE Computer Society},

address = {Washington DC, USA},

keywords = {audio-video fusion, computer vision, CVPR, speech reading},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2004-Shi-PNRPOSA,

title = {Propagation Networks for recognition of partially ordered sequential action},

author = {Y. Shi and Y. Huang and D. Minnen and A. Bobick and I. Essa},

year  = {2004},

date = {2004-01-01},

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

pages = {862-869},

publisher = {IEEE Computer Society},

address = {Washington, DC},

keywords = {activity recognition, computational video, computer vision, CVPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2003-Minnen-EGLHEAR,

title = {Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition},

author = {D. Minnen and I. Essa and T. Starner},

year  = {2003},

date = {2003-06-01},

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

pages = {626-632},

keywords = {activity recognition, computational video, computer vision, CVPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2001-Schodl-DLFO,

title = {Depth layers from occlusions},

author = {A. Schödl and I. Essa},

url = {http://www.cc.gatech.edu/cpl/projects/depthfromocclusion/},

doi = {http://dx.doi.org/10.1109/CVPR.2001.990534},

year  = {2001},

date = {2001-01-01},

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

volume = {1},

pages = {639 - 644},

publisher = {IEEE Computer Society Press},

address = {Kauai, HAWAI, US},

organization = {IEEE Computer Society},

keywords = {computer vision, CVPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2000-Haro-DTEUTPPDA,

title = {Detecting and Tracking Eyes By Using Their Physiological Properties, Dynamics, and Appearance},

author = {A. Haro and M. Flickner and I. Essa},

editor = {J. Ponce and J. Malik and D. Kriegman and D. Forsyth},

year  = {2000},

date = {2000-01-01},

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

volume = {1},

pages = {163--168},

publisher = {IEEE},

address = {Hilton Head Island, SC, USA},

organization = {IEEE},

keywords = {computer vision, CVPR},

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}

}