Publications

@conference{nokey,

title = {TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization},

author = {Sijie Zhu and Mubarak Shah and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/11695.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/11695-supp.pdf},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

keywords = {Cross-View, CVPR, Geo-Localization, Transformers},

pubstate = {published},

tppubtype = {conference}

}

@conference{RegmiICCV2021,

title = {Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing},

author = {Krishna Regmi and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/video_geolocalization_ICCV2021.pdf

https://github.com/kregmi/VTE},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {In this paper, we address the problem of video geolocalization by proposing a Geo-Temporal Feature Learning (GTFL) Network to simultaneously learn the discriminative features for the query video frames and the gallery images for estimating the geo-spatial trajectory of a query video. Based on a transformer encoder architecture, our

GTFL model encodes query and gallery data separately, via two dedicated branches. The proposed GPS Loss and Clip Triplet Loss exploit the geographical and temporal proximity between the frames and the clips to jointly learn the query and the gallery features. We also propose a deep learning approach to trajectory smoothing by predicting the outliers in the estimated GPS positions and learning the offsets to smooth the trajectory. We build a large dataset from four different regions of USA; New York, San Francisco, Berkeley and Bay Area using BDD driving videos as query, and by collecting corresponding Google StreetView (GSV) Images for gallery. Extensive

evaluations of proposed method on this new dataset are provided. Code and dataset details is publicly available at

https://github.com/kregmi/VTE.},

keywords = {Geo-Localization, ICCV, Transformers, Video Geo-localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{Gupta2020,

title = {RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery},

author = {Rohit Gupta and Mubarak Shah},

url = {https://arxiv.org/pdf/2004.07312.pdf},

year  = {2020},

date = {2020-04-15},

booktitle = {International Conference on Pattern Recognition},

keywords = {Geo-Localization, ICPR, Segmentation},

pubstate = {published},

tppubtype = {conference}

}

@conference{Regmi2019,

title = { Bridging the Domain Gap for Ground-to-Aerial Image Matching},

author = {Krishna Regmi and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/02/Publications_Bridging-the-Domain-Gap-for-Ground-to-Aerial-Image-Matching_Final.pdf

https://www.crcv.ucf.edu/research/projects/bridging-the-domain-gap-for-ground-to-aerial-image-matching/

},

year  = {2019},

date = {2019-10-27},

publisher = {International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2},

keywords = {Cross-View Image Retrieval, Geo-Localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{Regmi2018,

title = { Cross-View Image Synthesis Using Conditional GANs},

author = {Krishna Regmi and Ali Borji},

url = {https://www.crcv.ucf.edu/papers/cvpr2018/cross-view.pdf

https://www.crcv.ucf.edu/research/projects/cross-view-image-synthesis/},

year  = {2018},

date = {2018-04-06},

urldate = {2018-04-06},

publisher = { IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, June 18-22, 2018},

keywords = {Cross-View Image Synthesis, Geo-Localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{Ardeshir2015,

title = {Geo-semantic Segmentation},

author = {Shervin Ardeshir and Kofi Malcolm Collins-Sibley and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/cvpr2015/Geo-semantic_Segmentation.pdf

https://www.crcv.ucf.edu/projects/Geosemantic/

https://www.youtube.com/watch?v=jf5U3gdF5yEhttps://www.youtube.com/watch?v=jf5U3gdF5yE

},

year  = {2015},

date = {2015-01-29},

urldate = {2015-01-29},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015)},

keywords = {Deep Learning, Geo-Localization, REU, Semantic Segmentation},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zamir2014,

title = {GPS-Tag Refinement using Random Walks with an Adaptive Damping Factor},

author = {Amir Roshan Zamir and Shervin Ardeshir and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/cvpr2014/TagRefinement_CVPR14_Camready_v5.pdf

https://www.crcv.ucf.edu/papers/cvpr2014/video-spotlight-514.mp4

http://www.youtube.com/watch?v=0qbKQHJu-ow&list=PLd3hlSJsX_InWZEJNJG_yoGs-zy-9D-J7&feature=share},

year  = {2014},

date = {2014-01-26},

urldate = {2014-01-26},

publisher = {CVPR 2014},

keywords = {Deep Learning, Geo-Localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{Ardeshir2015b,

title = {GIS-Assisted Object Detection and Geospatial Localization},

author = {Shervin Ardeshir and Amir Roshan Zamir and Alejandro Torroella and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/GIS_ECCV14.pdf},

year  = {2014},

date = {2014-01-25},

urldate = {2014-01-25},

publisher = {ECCV 2014},

keywords = {Deep Learning, Geo-Localization, GIS, Object Detection, REU},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zamir2013,

title = {Visual Business Recognition - A Multimodal Approach},

author = {Amir Roshan Zamir and Afshin Dehghan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/ACM13_BizRec.pdf

http://youtu.be/EIr2Dkj-T-o

https://www.crcv.ucf.edu/projects/Business-Recognition/

},

year  = {2013},

date = {2013-01-16},

urldate = {2013-01-16},

publisher = {ACM Multimedia 2013},

keywords = {Deep Learning, Geo-Localization, Video Geo-localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{Vaca-Castano2012,

title = {City Scale Geo-Spatial Trajectory Estimation of a Moving Camera},

author = {Gonzalo Vaca-Castano and Amir Roshan Zamir and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/cvpr2012/CVPR12_Amir.pdf},

year  = {2012},

date = {2012-12-24},

urldate = {2012-12-24},

publisher = { Computer Vision and Pattern Recognition 2012},

keywords = {Deep Learning, Geo-Localization, Video Geo-localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zamir2011,

title = { Street View Challenge: Identification of Commercial Entities in Street View Imagery},

author = {Amir Roshan Zamir and Alexander Darino and Ryan Patrick and Mubarak Shah },

year  = {2011},

date = {2011-12-18},

urldate = {2011-12-18},

booktitle = {ICMLA},

keywords = {Geo-Localization, REU},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zamir2010,

title = {Accurate Image Localization Based on Google Maps Street View},

author = {Amir Roshan Zamir and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/eccv2010/Zamir_ECCV_2010.pdf},

year  = {2010},

date = {2010-12-12},

urldate = {2010-12-12},

publisher = {European Conference on Computer Vision (ECCV)},

keywords = {Deep Learning, Geo-Localization},

pubstate = {published},

tppubtype = {conference}

}