Publications

@inproceedings{2015-Thomaz-IMEARWSFASFS,

title = {Inferring Meal Eating Activities in Real World Settings from Ambient Sounds: A Feasibility Study},

author = {Edison Thomaz and Cheng Zhang and Irfan Essa and Gregory Abowd},

url = {https://dl.acm.org/doi/10.1145/2678025.2701405},

doi = {10.1145/2678025.2701405},

year  = {2015},

date = {2015-05-01},

urldate = {2015-05-01},

booktitle = {ACM Conference on Intelligence User Interfaces (IUI)},

abstract = {Dietary self-monitoring has been shown to be an effective method for weight-loss, but it remains an onerous task despite recent advances in food journaling systems. Semi-automated food journaling can reduce the effort of logging, but often requires that eating activities be detected automatically. In this work we describe results from a feasibility study conducted in-the-wild where eating activities were inferred from ambient sounds captured with a wrist-mounted device; twenty participants wore the device during one day for an average of 5 hours while performing normal everyday activities. Our system was able to identify meal eating with an F-score of 79.8% in a person-dependent evaluation, and with 86.6% accuracy in a person-independent evaluation. Our approach is intended to be practical, leveraging off-the-shelf devices with audio sensing capabilities in contrast to systems for automated dietary assessment based on specialized sensors.},

keywords = {ACM, activity recognition, AI, awards, behavioral imaging, best paper award, computational health, IUI, machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2014-Ahsan-CSEIUKCCA,

title = {Clustering Social Event Images Using Kernel Canonical Correlation Analysis},

author = {Unaiza Ahsan and Irfan Essa},

url = {https://openaccess.thecvf.com/content_cvpr_workshops_2014/W20/papers/Ahsan_Clustering_Social_Event_2014_CVPR_paper.pdf

https://smartech.gatech.edu/handle/1853/53656},

year  = {2014},

date = {2014-06-01},

urldate = {2014-06-01},

booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Women in Computing (WiC)},

abstract = {Sharing user experiences in form of photographs, tweets, text, audio and/or video has become commonplace in social networking websites. Browsing through large collections of social multimedia remains a cumbersome task. It requires a user to initiate textual search query and manually go through a list of resulting images to find relevant information. We propose an automatic clustering algorithm, which, given a large collection of images, groups them into clusters of different events using the image features and related metadata. We formulate this problem as a kernel canonical correlation clustering problem in which data samples from different modalities or ‘views’ are projected to a space where correlations between the samples’ projections are maximized. Our approach enables us to learn a semantic representation of potentially uncorrelated feature sets and this representation is clustered to give unique social events. Furthermore, we leverage the rich information associated with each uploaded image (such as usernames, dates/timestamps, etc.) and empirically determine which combination of feature sets yields the best clustering score for a dataset of 100,000 images.

},

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

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2013-Thomaz-TAAPCWREBWWC,

title = {Technological Approaches for Addressing Privacy Concerns when Recognizing Eating Behaviors with Wearable Cameras.},

author = {Edison Thomaz and Aman Parnami and Jonathan Bidwell and Irfan Essa and Gregory Abowd},

doi = {10.1145/2493432.2493509},

year  = {2013},

date = {2013-09-01},

urldate = {2013-09-01},

booktitle = {ACM International Joint Conference on Pervasive and Ubiquitous Computing (UBICOMP)},

keywords = {activity recognition, computational health, privacy, Ubicomp, ubiquitous computing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2013-Bettadapura-ABDDTSIAR,

title = {Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition},

author = {Vinay Bettadapura and Grant Schindler and Thomas Ploetz and Irfan Essa},

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

doi = {10.1109/CVPR.2013.338},

year  = {2013},

date = {2013-06-01},

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

organization = {IEEE Computer Society},

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

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2013-Thomaz-FIEMFFILHC,

title = {Feasibility of Identifying Eating Moments from First-Person Images Leveraging Human Computation},

author = {Edison Thomaz and Aman Parnami and Irfan Essa and Gregory Abowd},

doi = {10.1145/2526667.2526672},

year  = {2013},

date = {2013-01-01},

urldate = {2013-01-01},

booktitle = {Proceedings of ACM International SenseCam and Pervasive Imaging (SenseCam '13)},

keywords = {activity recognition, behavioral imaging, computational health, ubiquitous computing, wearable computing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2011-Thomaz-ITLADLAML,

title = {Interactive Techniques for Labeling Activities Of Daily Living to Assist Machine Learning},

author = {Edison Thomaz and Thoma Pleotz and Irfan Essa and Gregory Abowd},

url = {https://wish2011.wordpress.com/accepted-papers/

https://users.ece.utexas.edu/~ethomaz/papers/w1.pdf},

year  = {2011},

date = {2011-11-01},

urldate = {2011-11-01},

booktitle = {Proceedings of Workshop on Interactive Systems in Healthcare},

abstract = {Over the next decade, as healthcare continues its march away from the hospital and towards the home, logging and making sense of activities of daily living will play a key role in health modeling and life-long home care. Machine learning research has explored ways to automate the detection and quantification of these activities in sensor-rich environments. While we continue to make progress in developing practical and cost-effective activity sensing techniques, one large hurdle remains, obtaining labeled activity data to train activity recognition systems. In this paper, we discuss the process of gathering ground truth data with human participation for health modeling applications. In particular, we propose a criterion and design space containing five dimensions that we have identified as central to the characterization and evaluation of interactive labeling methods.

},

keywords = {activity recognition, behavioral imaging, computational health, wearable computing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2010-Hamid-PLUMSCSV,

title = {Player Localization Using Multiple Static Cameras for Sports Visualization},

author = {Raffay Hamid and Ramkrishan Kumar and Matthias Grundmann and Kihwan Kim and Irfan Essa and Jessica Hodgins},

url = {http://www.raffayhamid.com/sports_viz.shtml},

doi = {10.1109/CVPR.2010.5540142},

year  = {2010},

date = {2010-06-01},

urldate = {2010-06-01},

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

publisher = {IEEE Computer Society Press},

organization = {IEEE Computer Society},

keywords = {activity recognition, computer vision, CVPR, sports visualization},

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-Minnen-DSMEAGMPD,

title = {Detecting Subdimensional Motifs: An Efficient Algorithm for Generalized Multivariate Pattern Discovery},

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

url = {https://doi.org/10.1109/ICDM.2007.52},

doi = {10.1109/ICDM.2007.52},

year  = {2007},

date = {2007-10-01},

urldate = {2007-10-01},

booktitle = {IEEE International Conference on Data Mining (ICDM)},

abstract = {Discovering recurring patterns in time series data is a fundamental problem for temporal data mining. This paper addresses the problem of locating sub-dimensional motifs in real-valued, multivariate time series, which requires the simultaneous discovery of sets of recurring patterns along with the corresponding relevant dimensions. While many approaches to motif discovery have been developed, most are restricted to categorical data, univariate time series, or multivariate data in which the temporal patterns span all dimensions. In this paper, we present an expected linear-time algorithm that addresses a generalization of multivariate pattern discovery in which each motif may span only a subset of the dimensions. To validate our algorithm, we discuss its theoretical properties and empirically evaluate it using several data sets, including synthetic data and motion capture data collected by an on-body inertial sensor.

},

keywords = {activity recognition},

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-Hamid-UAASUEM,

title = {Unsupervised Analysis of Activity Sequences Using Event Motifs},

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

year  = {2006},

date = {2006-01-01},

booktitle = {Proceedings of ACM International Workshop on Video Surveillance and Sensor Networks (IWVSSN)},

organization = {ACM},

keywords = {activity recognition},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2005-Hamid-DCAFE,

title = {Discovery and Characterization of Activities from Event-Streams},

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

year  = {2005},

date = {2005-07-01},

booktitle = {Uncertainty in Artificial Intelligence (UAI)},

pages = {251-258},

address = {Edinburgh, SCOTLAND},

keywords = {activity recognition},

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-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{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}

}