2021
Regmi, Krishna; Shah, Mubarak
Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing Conference
International Conference on Computer Vision, 2021.
Abstract | Tags: Geo-Localization, ICCV, Transformers, Video Geo-localization | Links:
@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}
}
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.
Regmi, Krishna; Shah, Mubarak
Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing Conference
International Conference on Computer Vision, 2021.
Abstract | Tags: Geo-Localization, ICCV, Transformers, Video Geo-localization | Links:
@conference{RegmiICCV2021b,
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}
}
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.
Regmi, Krishna
Exploring Relationships Between Ground and Aerial Views by Synthesis and Matching PhD Thesis
University of Central Florida, 2021.
Tags: Cross-View, GAN, Geo-Localization, Ph.D. Dissertation, Video Geo-localization | Links:
@phdthesis{Regmi2021,
title = {Exploring Relationships Between Ground and Aerial Views by Synthesis and Matching},
author = {Krishna Regmi},
url = {https://stars.library.ucf.edu/etd2020/747/},
year = {2021},
date = {2021-08-02},
urldate = {2021-08-02},
school = {University of Central Florida},
keywords = {Cross-View, GAN, Geo-Localization, Ph.D. Dissertation, Video Geo-localization},
pubstate = {published},
tppubtype = {phdthesis}
}
Regmi, Krishna
Exploring Relationships Between Ground and Aerial Views by Synthesis and Matching PhD Thesis
University of Central Florida, 2021.
Tags: Cross-View, GAN, Geo-Localization, Ph.D. Dissertation, Video Geo-localization | Links:
@phdthesis{Regmi2021b,
title = {Exploring Relationships Between Ground and Aerial Views by Synthesis and Matching},
author = {Krishna Regmi},
url = {https://stars.library.ucf.edu/etd2020/747/},
year = {2021},
date = {2021-08-02},
urldate = {2021-08-02},
school = {University of Central Florida},
keywords = {Cross-View, GAN, Geo-Localization, Ph.D. Dissertation, Video Geo-localization},
pubstate = {published},
tppubtype = {phdthesis}
}
2014
Zamir, Amir Roshan; Shah, Mubarak
Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching Using Generalized Graphs Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014.
Tags: Deep Learning, Geo-Localization, Video Geo-localization | Links:
@article{Zamir2014b,
title = {Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching Using Generalized Graphs},
author = {Amir Roshan Zamir and Mubarak Shah},
url = {https://www.crcv.ucf.edu/papers/PAMI_Amir%20Zamir.pdf},
year = {2014},
date = {2014-01-29},
urldate = {2014-01-29},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
keywords = {Deep Learning, Geo-Localization, Video Geo-localization},
pubstate = {published},
tppubtype = {article}
}
Zamir, Amir Roshan; Shah, Mubarak
Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching Using Generalized Graphs Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014.
Tags: Deep Learning, Geo-Localization, Video Geo-localization | Links:
@article{Zamir2014bb,
title = {Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching Using Generalized Graphs},
author = {Amir Roshan Zamir and Mubarak Shah},
url = {https://www.crcv.ucf.edu/papers/PAMI_Amir%20Zamir.pdf},
year = {2014},
date = {2014-01-29},
urldate = {2014-01-29},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
keywords = {Deep Learning, Geo-Localization, Video Geo-localization},
pubstate = {published},
tppubtype = {article}
}
Zamir, Amir Roshan
Visual Geo-Localization and Location-Aware Image Understanding PhD Thesis
University of Central Florida, 2014.
Tags: Deep Learning, Geo-Localization, GMCP, Video Geo-localization | Links:
@phdthesis{Zamir2014c,
title = {Visual Geo-Localization and Location-Aware Image Understanding},
author = {Amir Roshan Zamir},
url = {https://www.crcv.ucf.edu/papers/theses/Thesis_Amir_Zamir.pdf},
year = {2014},
date = {2014-01-21},
urldate = {2014-01-21},
school = {University of Central Florida},
keywords = {Deep Learning, Geo-Localization, GMCP, Video Geo-localization},
pubstate = {published},
tppubtype = {phdthesis}
}
Zamir, Amir Roshan
Visual Geo-Localization and Location-Aware Image Understanding PhD Thesis
University of Central Florida, 2014.
Tags: Deep Learning, Geo-Localization, GMCP, Video Geo-localization | Links:
@phdthesis{Zamir2014cb,
title = {Visual Geo-Localization and Location-Aware Image Understanding},
author = {Amir Roshan Zamir},
url = {https://www.crcv.ucf.edu/papers/theses/Thesis_Amir_Zamir.pdf},
year = {2014},
date = {2014-01-21},
urldate = {2014-01-21},
school = {University of Central Florida},
keywords = {Deep Learning, Geo-Localization, GMCP, Video Geo-localization},
pubstate = {published},
tppubtype = {phdthesis}
}
2013
Zamir, Amir Roshan; Dehghan, Afshin; Shah, Mubarak
Visual Business Recognition - A Multimodal Approach Conference
ACM Multimedia 2013, 2013.
Tags: Deep Learning, Geo-Localization, Video Geo-localization | Links:
@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}
}
Zamir, Amir Roshan; Dehghan, Afshin; Shah, Mubarak
Visual Business Recognition - A Multimodal Approach Conference
ACM Multimedia 2013, 2013.
Tags: Deep Learning, Geo-Localization, Video Geo-localization | Links:
@conference{Zamir2013b,
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}
}
2012
Vaca-Castano, Gonzalo; Zamir, Amir Roshan; Shah, Mubarak
City Scale Geo-Spatial Trajectory Estimation of a Moving Camera Conference
Computer Vision and Pattern Recognition 2012, 2012.
Tags: Deep Learning, Geo-Localization, Video Geo-localization | Links:
@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}
}
Vaca-Castano, Gonzalo; Zamir, Amir Roshan; Shah, Mubarak
City Scale Geo-Spatial Trajectory Estimation of a Moving Camera Conference
Computer Vision and Pattern Recognition 2012, 2012.
Tags: Deep Learning, Geo-Localization, Video Geo-localization | Links:
@conference{Vaca-Castano2012b,
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}
}