1. 

   Spatio-Temporal Alignment of Non-Overlapping Sequences from Independently Panning Cameras

   Seyed Morteza Safdarnejad, Xiaoming Liu

   We tackle a novel scenario of spatio-temporal alignment of seuqences referred to as Nonoverlapping Sequences (NOS). NOS are captured by multiple freely panning handheld cameras whose field of views (FOV) might have no direct spatial overlap. With the popularity of mobile sensors, NOS rise when multiple cooperative users capture a ...

   Continue reading

   Keywords: Motion Compensation, activity recognition

2. 

   Temporally Robust Global Motion Compensation by Keypoint-based Congealing

   Seyed Morteza Safdarnejad, Yousef Atoum, Xiaoming Liu

   Global motion compensation (GMC) removes the impact of camera motion and creates a video in which the background appears static over the progression of time. Various vision problems, such as human activity recognition, background reconstruction, and multi-object tracking can benefit from GMC. Existing GMC algorithms rely on sequentially processing consecutive ...

   Continue reading

   Keywords: Motion Compensation, Activity Recognition

3. 

   Robust Global Motion Compensation in Presence of Predominant Foreground

   Seyed Morteza Safdarnejad, Xiaoming Liu, Lalita Udpa

   Global motion compensation (GMC) removes intentional and unwanted camera motion. GMC is widely applicable for video stitching and, as a pre-processing module, for motion-based video analysis. While state-of-the-art GMC algorithms generally estimate homography satisfactorily between consecutive frames, their performances deteriorate on real-world unconstrained videos, for instance, videos with predominant foreground ...

   Continue reading

   Keywords: Motion Compensation, Activity Recognition

4. 

   Sports Videos in the Wild (SVW): A Video Dataset for Sports Analysis

   Seyed Morteza Safdarnejad, Xiaoming Liu, Lalita Udpa, Brooks Andrus, John Wood, Dean Craven

   The amount of digital videos being created is increasing exponentially, e.g., YouTube has reached the upload rate of 100 hours of video per minute. A great deal of this growth is due to the tremendous popularity of smartphones and ubiquitous Internet access. This means that amateur-user generated videos form ...

   Continue reading

   Keywords: Activity Recognition, Database, Application

2017

• Fusing Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks
  Songyang Zhang, Jun Xiao, Xiaoming Liu, Yi Yang, Yueting Zhuang
  IEEE Transactions on Multimedia, Nov 2017, Vol. 20, No. 9, pp.2330-2343, , Nov. 2017 (Accepted)
  Bibtex | PDF
@article{ fusing-geometric-features-for-skeleton-based-action-recognition-using-multilayer-lstm-networks,
  author = { Songyang Zhang and Jun Xiao and Xiaoming Liu and Yi Yang and Yueting Zhuang },
  title = { Fusing Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks },
  journal = { IEEE Transactions on Multimedia, Nov 2017 },
  volume = { 20 },
  number = { 9 },
  month = { November },
  year = { 2017 },
  pages = { 2330--2343 },
}
• Spatio-temporal Alignment of Non-overlapping Sequences from Independently Panning Cameras
  Seyed Morteza Safdarnejad, Xiaoming Liu
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, Jul. 2017
  Bibtex | PDF | Project Webpage
@inproceedings{ spatio-temporal-alignment-of-non-overlapping-sequences-from-independently-panning-cameras,
  author = { Seyed Morteza Safdarnejad and Xiaoming Liu },
  title = { Spatio-temporal Alignment of Non-overlapping Sequences from Independently Panning Cameras },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Honolulu, HI },
  month = { July },
  year = { 2017 },
}
• On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks
  Songyang Zhang, Xiaoming Liu, Jun Xiao
  Proc. IEEE Winter Conference on Application of Computer Vision (WACV 2017), Santa Rosa, CA, Mar. 2017
  Bibtex | PDF
@inproceedings{ on-geometric-features-for-skeleton-based-action-recognition-using-multilayer-lstm-networks,
  author = { Songyang Zhang and Xiaoming Liu and Jun Xiao },
  title = { On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks },
  booktitle = { Proc. IEEE Winter Conference on Application of Computer Vision },
  address = { Santa Rosa, CA },
  month = { March },
  year = { 2017 },
}

2016

• Temporally Robust Global Motion Compensation by Keypoint-based Congealing
  Seyed Morteza Safdarnejad, Yousef Atoum, Xiaoming Liu
  Proc. European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, Oct. 2016
  Bibtex | PDF | Project Webpage | Code
@inproceedings{ temporally-robust-global-motion-compensation-by-keypoint-based-congealing,
  author = { Seyed Morteza Safdarnejad and Yousef Atoum and Xiaoming Liu },
  title = { Temporally Robust Global Motion Compensation by Keypoint-based Congealing },
  booktitle = { Proc. European Conference on Computer Vision },
  address = { Amsterdam, The Netherlands },
  month = { October },
  year = { 2016 },
}

2015

• Robust Global Motion Compensation in Presence of Predominant Foreground
  Seyed Morteza Safdarnejad, Xiaoming Liu, Lalita Udpa
  Proc. British Machine Vision Conference (BMVC 2015), Swansea, UK, Sep. 2015 (Acceptance rate 33%, Best Poster Award)
  Bibtex | PDF | Project Webpage
@inproceedings{ robust-global-motion-compensation-in-presence-of-predominant-foreground,
  author = { Seyed Morteza Safdarnejad and Xiaoming Liu and Lalita Udpa },
  title = { Robust Global Motion Compensation in Presence of Predominant Foreground },
  booktitle = { Proc. British Machine Vision Conference },
  address = { Swansea, UK },
  month = { September },
  year = { 2015 },
}
• Sports Videos in the Wild (SVW): A Video Dataset for Sports Analysis
  Seyed Morteza Safdarnejad, Xiaoming Liu, Lalita Udpa, Brooks Andrus, John Wood, Dean Craven
  Proc. International Conference on Automatic Face and Gesture Recognition (FG 2015), Ljubljana, Slovenia, May. 2015 (Acceptance rate 84/221 = 38%)
  Bibtex | PDF | Project Webpage
@inproceedings{ sports-videos-in-the-wild-svw-a-video-dataset-for-sports-analysis,
  author = { Seyed Morteza Safdarnejad and Xiaoming Liu and Lalita Udpa and Brooks Andrus and John Wood and Dean Craven },
  title = { Sports Videos in the Wild (SVW): A Video Dataset for Sports Analysis },
  booktitle = { Proc. International Conference on Automatic Face and Gesture Recognition },
  address = { Ljubljana, Slovenia },
  month = { May },
  year = { 2015 },
}

2014

• Genre Categorization of Amateur Sports Videos in the Wild
  Seyed Morteza Safdarnejad, Xiaoming Liu, Lalita Udpa
  Proc. International Conference on Image Processing (ICIP 2014), Paris, France, Oct. 2014
  Bibtex | PDF
@inproceedings{ genre-categorization-of-amateur-sports-videos-in-the-wild,
  author = { Seyed Morteza Safdarnejad and Xiaoming Liu and Lalita Udpa },
  title = { Genre Categorization of Amateur Sports Videos in the Wild },
  booktitle = { Proc. International Conference on Image Processing },
  address = { Paris, France },
  month = { October },
  year = { 2014 },
}

2012

• Spatio-Temporal Phrases for Activity Recognition
  Yimeng Zhang, Xiaoming Liu, Ming-Ching Chang, Weina Ge, Tsuhan Chen
  Proc. European Conference on Computer Vision (ECCV 2012), Firenze, Italy, Oct. 2012
  Bibtex | PDF
@inproceedings{ spatio-temporal-phrases-for-activity-recognition,
  author = { Yimeng Zhang and Xiaoming Liu and Ming-Ching Chang and Weina Ge and Tsuhan Chen },
  title = { Spatio-Temporal Phrases for Activity Recognition },
  booktitle = { Proc. European Conference on Computer Vision },
  address = { Firenze, Italy },
  month = { October },
  year = { 2012 },
}
• Group Context Learning for Event Recognition
  Yimeng Zhang, Weina Ge, Ming-Ching Chang, Xiaoming Liu
  Proc. IEEE Winter Conference on Application of Computer Vision (WACV 2012), Colorado, USA, Jan. 2012 (Oral presentation, acceptance rate 8%, Best Student Paper Award)
  Bibtex | PDF
@inproceedings{ group-context-learning-for-event-recognition,
  author = { Yimeng Zhang and Weina Ge and Ming-Ching Chang and Xiaoming Liu },
  title = { Group Context Learning for Event Recognition },
  booktitle = { Proc. IEEE Winter Conference on Application of Computer Vision },
  address = { Colorado, USA },
  month = { January },
  year = { 2012 },
}

2002

• Shot Boundary Detection Using Temporal Statistics Modeling
  Xiaoming Liu, Tsuhan Chen
  Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2002), Orlando, Florida, May. 2002 (Oral presentation)
  Bibtex | PDF
@inproceedings{ shot-boundary-detection-using-temporal-statistics-modeling,
  author = { Xiaoming Liu and Tsuhan Chen },
  title = { Shot Boundary Detection Using Temporal Statistics Modeling },
  booktitle = { Proc. International Conference on Acoustics, Speech, and Signal Processing },
  address = { Orlando, Florida },
  month = { May },
  year = { 2002 },
}