Publications

@inproceedings{2019-Hickson-FFLSRSNP,

title = {Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction},

author = {Steven Hickson and Karthik Raveendran and Alireza Fathi and Kevin Murphy and Irfan Essa},

url = {https://arxiv.org/abs/1906.06792

https://openaccess.thecvf.com/content_ICCVW_2019/papers/GMDL/Hickson_Floors_are_Flat_Leveraging_Semantics_for_Real-Time_Surface_Normal_Prediction_ICCVW_2019_paper.pdf},

doi = {10.1109/ICCVW.2019.00501},

year  = {2019},

date = {2019-10-01},

urldate = {2019-10-01},

booktitle = {IEEE International Conference on Computer Vision (ICCV) Workshop on Geometry Meets Deep Learning},

abstract = {We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the "ground truth" surface normals in the training set to ensure consistency with the semantic labels; (2) concurrently train on a mix of real and synthetic data, instead of pretraining on synthetic and fine-tuning on real; (3) jointly predict normals and semantics using a shared model, but only backpropagate errors on pixels that have valid training labels; (4) slim down the model and use grayscale instead of color inputs. Despite the simplicity of these steps, we demonstrate consistently improved state of the art results on several datasets, using a model that runs at 12 fps on a standard mobile phone.

},

howpublished = {arXiv preprint arXiv:1906.06792},

keywords = {computer vision, google, ICCV},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2011-Kim-GPRFAMT,

title = {Gaussian Process Regression Flow for Analysis of Motion Trajectories},

author = {K. Kim and D. Lee and I. Essa},

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

year  = {2011},

date = {2011-11-01},

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

publisher = {IEEE Computer Society},

keywords = {computer vision, ICCV},

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{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-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{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}

}