Publications

@inproceedings{2010-Kim-MFPPEDSS,

title = {Motion Field to Predict Play Evolution in Dynamic Sport Scenes},

author = {K. Kim and M. Grundmann and A. Shamir and I. Matthews and J. Hodgins and I. Essa},

doi = {10.1109/CVPR.2010.5540128},

year  = {2010},

date = {2010-06-01},

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

keywords = {computer vision, CVPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2007-Hamid-SFSUAAUST,

title = {Structure from Statistics - Unsupervised Activity Analysis using Suffix Trees},

author = {R. Hamid and S. Maddi and A. Bobick and I. Essa},

url = {http://dx.doi.org/10.1109/ICCV.2007.4408894

},

doi = {10.1109/ICCV.2007.4408894},

year  = {2007},

date = {2007-10-14},

urldate = {2007-10-14},

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

publisher = {IEEE Computer Society Press},

abstract = {Models of activity structure for unconstrained environments are generally not available a priori. Recent representational approaches to this end are limited by their computational complexity and ability to capture activity structure only up to some fixed temporal scale. In this work, we propose Suffix Trees as an activity representation to efficiently extract the structure of activities by analyzing their constituent event subsequences over multiple temporal scales. We empirically compare Suffix Trees with some of the previous approaches in terms of feature cardinality, discriminative prowess, noise sensitivity, and activity-class discovery. Finally, exploiting the properties of Suffix Trees, we present a novel perspective on anomalous subsequences of activities and propose an algorithm to detect them in linear time. We present comparative results over experimental data collected from a kitchen environment to demonstrate the competence of our proposed framework.

},

keywords = {activity discovery, activity recognition, computer vision, ICCV, IEEE},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2007-Yin-TCBVS,

title = {Tree-based Classifiers for Bilayer Video Segmentation},

author = {P. Yin and A. Criminisi and J. Winn and I. Essa},

year  = {2007},

date = {2007-06-01},

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

pages = {pp 1--8},

publisher = {IEEE Computer Society},

address = {Minneapolis, MN, USA},

keywords = {computational video, computer vision, CVPR, video segmentation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2006-Shi-LTSMFPLD,

title = {Learning Temporal Sequence Model from Partially Labeled Data},

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

year  = {2006},

date = {2006-06-01},

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

pages = {1631 - 1638},

publisher = {IEEE Computer Society},

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

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2006-Choi-EEMVFC,

title = {Element-Free Elastic Models for Volume Fitting and Capture},

author = {J. Choi and A. Szymczak and G. Turk and I. Essa},

url = {https://ieeexplore.ieee.org/document/1641028},

doi = {10.1109/CVPR.2006.110},

year  = {2006},

date = {2006-01-01},

urldate = {2006-01-01},

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

volume = {2},

pages = {2245--2252},

abstract = {We present a new method of fitting an element-free volumetric model to a sequence of deforming surfaces of a moving object. Given a sequence of visual hulls, we iteratively fit an element-free elastic model to the visual hull in order to extract the optimal pose of the captured volume. The fitting of the volumetric model is acheived by minimizing a combination of elastic potential energy, a surface distance measure, and a self-intersection penalty for each frame. A unique aspect of our work is that the model is mesh free - since the model is represented as a point cloud, it is easy to construct, manipulate and update the model as needed. Additionally, linear elasicity with rotation compensation makes it possible to handle local deformations and large rotations of body parts much more efficiently than other volume fitting approaches. Our experimental results for volume fitting and capture in a multi-view camera setting demonstrate the robustness of element-free elastic models against noise and self-occlusions.

},

keywords = {computer vision, CVPR, shape modeling},

pubstate = {published},

tppubtype = {inproceedings}

}

@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{2005-Hamid-UADCFE,

title = {Unsupervised Activity Discovery and Characterization From Event-Streams},

author = {Raffay Hamid and Siddhartha Maddi and Amos Johnson and Aaron Bobick and Irfan Essa and Charles Isbell},

url = {https://arxiv.org/abs/1207.1381

https://arxiv.org/pdf/1207.1381},

doi = {10.48550/arXiv.1207.1381},

year  = {2005},

date = {2005-01-01},

urldate = {2005-01-01},

booktitle = {Proceedings of The Learning Workshop at Snowbird},

address = {Snowbird, Utah},

abstract = {We present a framework to discover and characterize different classes of everyday activities from event-streams. We begin by representing activities as bags of event n-grams. This allows us to analyze the global structural information of activities, using their local event statistics. We demonstrate how maximal cliques in an undirected edge-weighted graph of activities, can be used for activity-class discovery in an unsupervised manner. We show how modeling an activity as a variable length Markov process, can be used to discover recurrent event-motifs to characterize the discovered activity-classes. We present results over extensive data-sets, collected from multiple active environments, to show the competence and generalizability of our proposed framework.

},

keywords = {activity discovery, activity recognition, computer vision, machine learning},

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{2003-Ruddarraju-PUIUVT,

title = {Perceptual User Interfaces using Vision-Based Eye Tracking},

author = {Ravi Ruddarraju and Antonio Haro and Kris Nagel and Quan Tran and Irfan Essa and Gregory Abowd and Elizabeth Mynatt},

url = {https://doi.org/10.1145/958432.958475},

doi = {10.1145/958432.958475},

year  = {2003},

date = {2003-01-01},

urldate = {2003-01-01},

booktitle = {International Conference on Multimodal Interfaces (ICMI)},

address = {Vancouver, Canada},

abstract = {We present a multi-camera vision-based eye tracking method to robustly locate and track user's eyes as they interact with an application. We propose enhancements to various vision-based eye-tracking approaches, which include (a) the use of multiple cameras to estimate head pose and increase coverage of the sensors and (b) the use of probabilistic measures incorporating Fisher's linear discriminant to robustly track the eyes under varying lighting conditions in real-time. We present experiments and quantitative results to demonstrate the robustness of our eye tracking in two application prototypes.



},

keywords = {computer vision, eye-tracking, ICMI, multimodal interfaces},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2003-Haro-EBST,

title = {Exemplar Based Surface Texture},

author = {Antonio Haro and Irfan Essa},

editor = {T Ertl. and B. Girod and G. Greiner and H. Niemann and H. -P. Seidel and E. Steinbach and R. Westermann},

year  = {2003},

date = {2003-01-01},

urldate = {2003-01-01},

booktitle = {Proceedings of Conference on Vision, Modeling, and Visualization},

pages = {95--101},

publisher = {Akademische Verlagsgesellschaft Aka GmbH, Berlin},

address = {Munich, Germany},

organization = {Computer Graphics & Visualization Group and the Media Technology Group of Technische Universitat Munchen},

keywords = {computer graphics, computer vision, video textures},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2003-Steedly-SPSFM,

title = {Spectral Partitioning for Structure from Motion},

author = {D. Steedly and I. Essa and F. Dellaert},

year  = {2003},

date = {2003-01-01},

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

pages = {996--1003},

publisher = {IEEE Computer Society},

address = {Nice, France},

keywords = {computer vision, ICCV},

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{2001-Steedly-PIINLSFM,

title = {Propagation of Innovative Information in Non-Linear Least-Squares Structure from Motion},

author = {D. Steedly and I. Essa},

year  = {2001},

date = {2001-01-01},

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

volume = {2},

pages = {223--229},

address = {Vancouver, Canada},

keywords = {computer vision, ICCV},

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{1999-Moore-EHAOCRT,

title = {Exploiting Human Actions and Object Context for Recognition Tasks},

author = {D. Moore and I. Essa and M. Hayes},

url = {https://ieeexplore.ieee.org/document/791201

},

doi = {10.1109/ICCV.1999.791201},

year  = {1999},

date = {1999-01-01},

urldate = {1999-01-01},

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

pages = {80--86},

address = {Corfu, Greece},

organization = {IEEE Computer Society},

abstract = {Our goal is to exploit human motion and object context to perform action recognition and object classification. Towards this end, we introduce a framework for recognizing actions and objects by measuring image-, object- and action-based information from video. Hidden Markov models are combined with object context to classify hand actions, which are aggregated by a Bayesian classifier to summarize activities. We also use Bayesian methods to differentiate the class of unknown objects by evaluating detected actions along with low-level, extracted object features. Our approach is appropriate for locating and classifying objects under a variety of conditions including full occlusion. We show experiments where both familiar and previously unseen objects are recognized using action and context information.

},

keywords = {activity recognition, computer vision, ICCV},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{1999-Brostow-MBDV,

title = {Motion Based Decompositing of Video},

author = {G. J. Brostow and I. Essa},

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

doi = {http://dx.doi.org/10.1109/ICCV.1999.791190},

year  = {1999},

date = {1999-01-01},

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

volume = {1},

pages = {8--13},

publisher = {IEEE Computer Society},

keywords = {computer vision, ICCV},

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}

}