Publications

@inproceedings{2015-Bettadapura-LCSAFRR,

title = {Leveraging Context to Support Automated Food Recognition in Restaurants},

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

url = {http://www.vbettadapura.com/egocentric/food/},

doi = {10.1109/WACV.2015.83},

year  = {2015},

date = {2015-01-01},

booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},

publisher = {IEEE Computer Society},

keywords = {computer vision, WACV},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2015-Hickson-SILLHS,

title = {Semantic Instance Labeling Leveraging Hierarchical Segmentation},

author = {Steven Hickson and Irfan Essa and Henrik Christensen},

doi = {10.1109/WACV.2015.147},

year  = {2015},

date = {2015-01-01},

booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},

publisher = {IEEE Computer Society},

keywords = {computer vision, WACV},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2015-Raza-FTCOBUSL,

title = {Finding Temporally Consistent Occlusion Boundaries using Scene Layout},

author = {Syed Hussain Raza and Ahmad Humayun and Matthias Grundmann and David Anderson and Irfan Essa},

doi = {10.1109/WACV.2015.141},

year  = {2015},

date = {2015-01-01},

booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},

publisher = {IEEE Computer Society},

keywords = {computer vision, WACV},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2015-Bettadapura-EFLUFPD,

title = {Egocentric Field-of-View Localization Using First-Person Point-of-View Devices},

author = {Vinay Bettadapura and Irfan Essa and Caroline Pantofaru},

url = {https://ieeexplore.ieee.org/document/7045943

http://www.vbettadapura.com/egocentric/localization/},

doi = {10.1109/WACV.2015.89},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},

publisher = {IEEE Computer Society},

abstract = {We present a technique that uses images, videos and sensor data taken from first-person point-of-view devices to perform egocentric field-of-view (FOV) localization. We define egocentric FOV localization as capturing the visual information from a person's field-of-view in a given environment and transferring this information onto a reference corpus of images and videos of the same space, hence determining what a person is attending to. Our method matches images and video taken from the first-person perspective with the reference corpus and refines the results using the first-person's head orientation information obtained using the device sensors. We demonstrate single and multi-user egocentric FOV localization in different indoor and outdoor environments with applications in augmented reality, event understanding and studying social interactions.

},

keywords = {awards, best paper award, computer vision, WACV, wearable computing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2014-Bidwell-MCVAUMHTFCDSC,

title = {Measuring child visual attention using markerless head tracking from color and depth sensing cameras},

author = {Jonathan Bidwell and Irfan Essa and Agata Rozga and Gregory Abowd},

url = {https://dl.acm.org/doi/10.1145/2663204.2663235

http://icmi.acm.org/2014/},

doi = {10.1145/2663204.2663235},

year  = {2014},

date = {2014-11-01},

urldate = {2014-11-01},

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

abstract = {A child's failure to respond to his or her name being called is an early warning sign for autism and response to name is currently assessed as a part of standard autism screening and diagnostic tools. In this paper, we explore markerless child head tracking as an unobtrusive approach for automatically predicting child response to name. Head turns are used as a proxy for visual attention. We analyzed 50 recorded response to name sessions with the goal of predicting if children, ages 15 to 30 months, responded to name calls by turning to look at an examiner within a defined time interval. The child's head turn angles and hand annotated child name call intervals were extracted from each session. Human assisted tracking was employed using an overhead Kinect camera, and automated tracking was later employed using an additional forward facing camera as a proof-of-concept. We explore two distinct analytical approaches for predicting child responses, one relying on rule-based approached and another on random forest classification. In addition, we derive child response latency as a new measurement that could provide researchers and clinicians with finer grain quantitative information currently unavailable in the field due to human limitations. Finally we reflect on steps for adapting our system to work in less constrained natural settings.



},

keywords = {autism, behavioral imaging, computer vision, ICMI},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2014-Sharma-VBAOUSMT,

title = {Video Based Assessment of OSATS Using Sequential Motion Textures},

author = {Yachna Sharma and Vinay Bettadapura and Thomas Ploetz and Nils Hammerla and Sebastian Mellor and Roisin McNaney and Patrick Olivier and Sandeep Deshmukh and Andrew Mccaskie and Irfan Essa},

url = {https://smartech.gatech.edu/bitstream/handle/1853/53651/2014-Sharma-VBAOUSMT.pdf

https://www.semanticscholar.org/paper/Video-Based-Assessment-of-OSATS-Using-Sequential-Sharma-Bettadapura/1dde770faa24d4e04306ca6fb85e76dc78876c49},

year  = {2014},

date = {2014-09-01},

urldate = {2014-09-01},

booktitle = {Proceedings of Workshop on Modeling and Monitoring of Computer Assisted Interventions (M2CAI)},

abstract = {A fully automated framework for video-based surgical skill assessment is presented that incorporates the sequential and qualitative aspects of surgical motion in a data-driven manner. The Objective Structured Assessment of Technical Skills (OSATS) assessments is replicated, which provides both an overall and in-detail evaluation of basic suturing skills required for surgeons. Video analysis techniques are introduced that incorporate sequential motion aspects into motion textures. Significant performance improvement over standard bag-of-words and motion analysis approaches is demonstrated. The framework is evaluated in a case study that involved medical students with varying levels of expertise performing basic surgical tasks in a surgical training lab setting.



},

keywords = {activity assessment, awards, best paper award, computer vision, medical imaging, surgical training},

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{2014-Hickson-EHGSRV,

title = {Efficient Hierarchical Graph-Based Segmentation of RGBD Videos},

author = {Steven Hickson and Stan Birchfield and Irfan Essa and Henrik Christensen},

url = {http://www.cc.gatech.edu/cpl/projects/4dseg},

year  = {2014},

date = {2014-06-01},

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

organization = {IEEE Computer Society},

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

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2013-Rehg-DCSB,

title = {Decoding Children's Social Behavior},

author = {James Rehg and Gregory Abowd and Agata Rozga and Mario Romero and Mark Clements and Stan Sclaroff and Irfan Essa and Opal Ousley and Yin Li and Chanho Kim and Hrishikesh Rao and Jonathan Kim and Liliana Lo Presti and Jianming Zhang and Denis Lantsman and Jonathan Bidwell and Zhefan Ye},

url = {https://ieeexplore.ieee.org/document/6619282

http://www.cbi.gatech.edu/mmdb/

},

doi = {10.1109/CVPR.2013.438},

isbn = {1063-6919},

year  = {2013},

date = {2013-06-01},

urldate = {2013-06-01},

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

organization = {IEEE Computer Society},

abstract = {We introduce a new problem domain for activity recognition: the analysis of children's social and communicative behaviors based on video and audio data. We specifically target interactions between children aged 1-2 years and an adult. Such interactions arise naturally in the diagnosis and treatment of developmental disorders such as autism. We introduce a new publicly-available dataset containing over 160 sessions of a 3-5 minute child-adult interaction. In each session, the adult examiner followed a semi-structured play interaction protocol which was designed to elicit a broad range of social behaviors. We identify the key technical challenges in analyzing these behaviors, and describe methods for decoding the interactions. We present experimental results that demonstrate the potential of the dataset to drive interesting research questions, and show preliminary results for multi-modal activity recognition.

},

keywords = {autism, behavioral imaging, computational health, computer vision, CVPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2013-Raza-GCFV,

title = {Geoemetric Context from Video},

author = {Syed Hussain Raza and Matthias Grundmann and Irfan Essa},

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

doi = {10.1109/CVPR.2013.396},

year  = {2013},

date = {2013-06-01},

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

organization = {IEEE Computer Society},

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

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{2012-Hartmann-WSLOSFWV,

title = {Weakly Supervised Learning of Object Segmentations from Web-Scale Videos},

author = {Glenn Hartmann and Matthias Grundmann and Judy Hoffman and David Tsai and Vivek Kwatra and Omid Madani and Sudheendra Vijayanarasimhan and Irfan Essa and James Rehg and Rahul Sukthankar},

url = {https://link.springer.com/chapter/10.1007/978-3-642-33863-2_20

https://research.google.com/pubs/archive/40735.pdf

},

doi = {10.1007/978-3-642-33863-2_20},

year  = {2012},

date = {2012-10-01},

urldate = {2012-10-01},

booktitle = {Proceedings of ECCV 2012 Workshop on Web-scale Vision and Social Media},

abstract = {We propose to learn pixel-level segmentations of objects from weakly labeled (tagged) internet videos. Specifically, given a large collection of raw YouTube content, along with potentially noisy tags, our goal is to automatically generate spatiotemporal masks for each object, such as “dog”, without employing any pre-trained object detectors. We formulate this problem as learning weakly supervised classifiers for a set of independent spatio-temporal segments. The object seeds obtained using segment-level classifiers are further refined using graphcuts to generate high-precision object masks. Our results, obtained by training on a dataset of 20,000 YouTube videos weakly tagged into 15 classes, demonstrate automatic extraction of pixel-level object masks. Evaluated against a ground-truthed subset of 50,000 frames with pixel-level annotations, we confirm that our proposed methods can learn good object masks just by watching YouTube.



},

keywords = {awards, best paper award, computer vision, ECCV, machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2012-Kim-DRIDSWCM,

title = {Detecting Regions of Interest in Dynamic Scenes with Camera Motions},

author = {Kihwan Kim and Dongreyol Lee and Irfan Essa},

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

doi = {10.1109/CVPR.2012.6247809},

year  = {2012},

date = {2012-01-01},

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

publisher = {IEEE Computer Society},

keywords = {computer vision, CVPR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2012-Grundmann-CRSR,

title = {Calibration-Free Rolling Shutter Removal},

author = {Matthias Grundmann and Vivek Kwatra and Daniel Castro and Irfan Essa},

url = {http://www.cc.gatech.edu/cpl/projects/rollingshutter/

https://research.google.com/pubs/archive/37744.pdf

https://youtu.be/_Pr_fpbAok8},

doi = {10.1109/ICCPhot.2012.6215213},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {IEEE Conference on Computational Photography (ICCP)},

publisher = {IEEE Computer Society},

abstract = {We present a novel algorithm for efficient removal of rolling shutter distortions in uncalibrated streaming videos. Our proposed method is calibration free as it does not need any knowledge of the camera used, nor does it require calibration using specially recorded calibration sequences. Our algorithm can perform rolling shutter removal under varying focal lengths, as in videos from CMOS cameras equipped with an optical zoom. We evaluate our approach across a broad range of cameras and video sequences demonstrating robustness, scaleability, and repeatability. We also conducted a user study, which demonstrates preference for the output of our algorithm over other state-of-the art methods. Our algorithm is computationally efficient, easy to parallelize, and robust to challenging artifacts introduced by various cameras with differing technologies.

},

keywords = {awards, best paper award, computational photography, computational video, computer graphics, computer vision, ICCP},

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{2011-Grundmann-AVSWROCP,

title = {Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths},

author = {M. Grundmann and V. Kwatra and I. Essa},

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

doi = {10.1109/CVPR.2011.5995525},

year  = {2011},

date = {2011-06-01},

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

publisher = {IEEE Computer Society},

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

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2011-Sarin-3VORUAMCNPESSE,

title = {3-Dimensional Visualization of the Operating Room Using Advanced Motion Capture: A Novel Paradigm to Expand Simulation-Based Surgical Education},

author = {Eric Sarin and Kihwan Kim and Irfan Essa and William Cooper},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Proceedings of Society of Thoracic Surgeons Annual Meeting},

publisher = {Society of Thoracic Surgeons},

keywords = {computational health, computer vision, intelligent environments, surgical training},

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{2010-Grundmann-EHGVS,

title = {Efficient Hierarchical Graph-Based Video Segmentation},

author = {M. Grundmann and V. Kwatra and M. Han and I. Essa},

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

doi = {10.1109/CVPR.2010.5539893},

year  = {2010},

date = {2010-06-01},

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

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

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2010-Grundmann-DSVR,

title = {Discontinuous Seam-Carving for Video Retargeting},

author = {M. Grundmann and V. Kwatra and M. Han and I. Essa},

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

doi = {10.1109/CVPR.2010.5540165},

year  = {2010},

date = {2010-06-01},

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

publisher = {IEEE Computer Society},

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

pubstate = {published},

tppubtype = {inproceedings}

}