Publications

@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{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{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}

}