Publications

@conference{Sun2020,

title = {Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking},

author = {ShiJie Sun and Naveed Akhtar and XiangYu Song and HuanSheng Song and Ajmal Mian and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Simultaneous-Detection-and-Tracking-with-Motion-Modelling-for-Multiple-Object-Tracking.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Simultaneous-Detection-and-Tracking-with-Motion-Modelling-for-Multiple-Object-Tracking_Supp.pdf 

https://shijies.github.io/DMMN_Page/},

year  = {2020},

date = {2020-08-23},

booktitle = {16th European Conference on Computer Vision},

abstract = {Deep learning based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection. This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this issue, we introduce Deep Motion Modeling Network (DMM-Net) that can estimate multiple objects’ motion parameters to perform joint detection and association in an end-to-end manner. DMM-Net models object features over multiple frames and simultaneously infers object classes, visibility and their motion parameters. These outputs are readily used to update the tracklets for efficient MOT. DMM-Net achieves PR-MOTA score of 12.80 @ 120+ fps for the popular UA-DETRAC challenge - which is better performance and orders of magnitude faster. We also contribute a synthetic large-scale public dataset Omni-MOT for vehicle tracking that provides precise ground-truth annotations to eliminate the detector influence in MOT evaluation. This 14M+ frames dataset is extendable with our public script (Code at Dataset, Dataset Recorder, Omni-MOT Source). We demonstrate the suitability of Omni-MOT for deep learning with DMM-Net, and also make the source code of our network public.},

keywords = {ECCV, Tracking},

pubstate = {published},

tppubtype = {conference}

}

@conference{Sun2020b,

title = {Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking},

author = {ShiJie Sun and Naveed Akhtar and XiangYu Song and HuanSheng Song and Ajmal Mian and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Simultaneous-Detection-and-Tracking-with-Motion-Modelling-for-Multiple-Object-Tracking.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Simultaneous-Detection-and-Tracking-with-Motion-Modelling-for-Multiple-Object-Tracking_Supp.pdf 

https://shijies.github.io/DMMN_Page/},

year  = {2020},

date = {2020-08-23},

booktitle = {16th European Conference on Computer Vision},

abstract = {Deep learning based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection. This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this issue, we introduce Deep Motion Modeling Network (DMM-Net) that can estimate multiple objects’ motion parameters to perform joint detection and association in an end-to-end manner. DMM-Net models object features over multiple frames and simultaneously infers object classes, visibility and their motion parameters. These outputs are readily used to update the tracklets for efficient MOT. DMM-Net achieves PR-MOTA score of 12.80 @ 120+ fps for the popular UA-DETRAC challenge - which is better performance and orders of magnitude faster. We also contribute a synthetic large-scale public dataset Omni-MOT for vehicle tracking that provides precise ground-truth annotations to eliminate the detector influence in MOT evaluation. This 14M+ frames dataset is extendable with our public script (Code at Dataset, Dataset Recorder, Omni-MOT Source). We demonstrate the suitability of Omni-MOT for deep learning with DMM-Net, and also make the source code of our network public.},

keywords = {ECCV, Tracking},

pubstate = {published},

tppubtype = {conference}

}

@conference{Tian2017,

title = {On Duality Of Multiple Target Tracking and Semgentation},

author = {Yicong Tian and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/1610.04542.pdf},

year  = {2016},

date = {2016-03-18},

publisher = {Cornell University Library},

keywords = {Segmentation, Tracking},

pubstate = {published},

tppubtype = {conference}

}

@conference{Tian2017d,

title = {On Duality Of Multiple Target Tracking and Semgentation},

author = {Yicong Tian and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/1610.04542.pdf},

year  = {2016},

date = {2016-03-18},

publisher = {Cornell University Library},

keywords = {Segmentation, Tracking},

pubstate = {published},

tppubtype = {conference}

}

@conference{Izadinia2012c,

title = {GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs},

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

url = {https://www.crcv.ucf.edu/papers/eccv2012/GMCP-Tracker_ECCV12.pdf 

http://youtu.be/f4Muu1d7NhA},

year  = {2012},

date = {2012-12-26},

urldate = {2012-12-26},

publisher = {European Conference on Computer Vision 2012},

keywords = {Clustering, Deep Learning, GMCP, Tracking},

pubstate = {published},

tppubtype = {conference}

}

@conference{Izadinia2012cb,

title = {GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs},

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

url = {https://www.crcv.ucf.edu/papers/eccv2012/GMCP-Tracker_ECCV12.pdf 

http://youtu.be/f4Muu1d7NhA},

year  = {2012},

date = {2012-12-26},

urldate = {2012-12-26},

publisher = {European Conference on Computer Vision 2012},

keywords = {Clustering, Deep Learning, GMCP, Tracking},

pubstate = {published},

tppubtype = {conference}

}

@conference{Khan2006b,

title = {A Multiview Approach to Tracking People in Crowded Scenes using a Planar Homography Constraint},

author = {Saad M. Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/Khan_ECCV06.pdf},

year  = {2006},

date = {2006-11-19},

urldate = {2006-11-19},

publisher = {European Conference of Computer Vision},

keywords = {Deep Learning, Multi-view, Tracking},

pubstate = {published},

tppubtype = {conference}

}

@conference{Khan2006bb,

title = {A Multiview Approach to Tracking People in Crowded Scenes using a Planar Homography Constraint},

author = {Saad M. Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/Khan_ECCV06.pdf},

year  = {2006},

date = {2006-11-19},

urldate = {2006-11-19},

publisher = {European Conference of Computer Vision},

keywords = {Deep Learning, Multi-view, Tracking},

pubstate = {published},

tppubtype = {conference}

}