Michael Jones

- Phone: 617-621-7587
- Email:
-
Position:
Research / Technical Staff
Senior Principal Research Scientist -
Education:
Ph.D., Massachusetts Institute of Technology, 1997 -
Research Areas:
External Links:
Mike's Quick Links
-
Biography
Mike's main areas of interest are computer vision, machine learning and data mining. He has focused on algorithms for detecting and analyzing people in images and video including face detection and recognition and pedestrian detection. He is a co-inventor of the popular Viola-Jones face detection method. Mike has been awarded the Marr Prize at ICCV and the Longuet-Higgins Prize at CVPR.
-
Recent News & Events
-
NEWS MERL researchers presenting four papers and organizing two workshops at CVPR 2020 conference Date: June 14, 2020 - June 19, 2020
MERL Contacts: Anoop Cherian; Michael Jones; Toshiaki Koike-Akino; Tim Marks; Kuan-Chuan Peng; Ye Wang
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief- MERL researchers are presenting four papers (two oral papers and two posters) and organizing two workshops at the IEEE/CVF Computer Vision and Pattern Recognition (CVPR 2020) conference.
CVPR 2020 Orals with MERL authors:
1. "Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction," by Maosen Li, Siheng Chen, Yangheng Zhao, Ya Zhang, Yanfeng Wang, Qi Tian
2. "Collaborative Motion Prediction via Neural Motion Message Passing," by Yue Hu, Siheng Chen, Ya Zhang, Xiao Gu
CVPR 2020 Posters with MERL authors:
3. "LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood," by Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Ye Wang, Michael Jones, Anoop Cherian, Toshiaki Koike-Akino, Xiaoming Liu, Chen Feng
4. "MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird’s Eye View Maps," by Pengxiang Wu, Siheng Chen, Dimitris N. Metaxas
CVPR 2020 Workshops co-organized by MERL researchers:
1. Fair, Data-Efficient and Trusted Computer Vision
2. Deep Declarative Networks.
- MERL researchers are presenting four papers (two oral papers and two posters) and organizing two workshops at the IEEE/CVF Computer Vision and Pattern Recognition (CVPR 2020) conference.
-
NEWS MERL presents three papers at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Date: June 27, 2016 - June 30, 2016
Where: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV
MERL Contacts: Michael Jones; Tim Marks
Research Area: Machine LearningBrief- MERL researchers in the Computer Vision group presented three papers at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), which had a paper acceptance rate of 29.9%.
See All News & Events for Mike -
-
Awards
-
AWARD CVPR 2011 Longuet-Higgins Prize Date: June 25, 2011
Awarded to: Paul A. Viola and Michael J. Jones
Awarded for: "Rapid Object Detection using a Boosted Cascade of Simple Features"
Awarded by: Conference on Computer Vision and Pattern Recognition (CVPR)
MERL Contact: Michael Jones
Research Area: Machine LearningBrief- Paper from 10 years ago with the largest impact on the field: "Rapid Object Detection using a Boosted Cascade of Simple Features", originally published at Conference on Computer Vision and Pattern Recognition (CVPR 2001).
-
-
Research Highlights
-
MERL Publications
- "Perceptual Metric Learning for Video Anomaly Detection", Machine Vision and Applications, DOI: 0.1007/s00138-021-01187-5, Vol. 32, No. 63, March 2021.BibTeX TR2021-028 PDF
- @article{Ramachandra2021mar,
- author = {Ramachandra, Bharathkumar and Jones, Michael J. and Vatsavai, Ranga},
- title = {Perceptual Metric Learning for Video Anomaly Detection},
- journal = {Machine Vision and Applications},
- year = 2021,
- volume = 32,
- number = 63,
- month = mar,
- doi = {0.1007/s00138-021-01187-5},
- url = {https://www.merl.com/publications/TR2021-028}
- }
, - "Knowledge Distillation Thrives on Data Augmentation", arXiv, December 2020. ,
- "Multi-Head Knowledge Distillation for Model Compression", arXiv, December 2020. ,
- "A Survey of Single-Scene Video Anomaly Detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2020.3040591, November 2020.BibTeX TR2021-029 PDF
- @article{Jones2020nov,
- author = {Jones, Michael J. and Ramachandra, Bharathkumar and Vatsavai, Ranga},
- title = {A Survey of Single-Scene Video Anomaly Detection},
- journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
- year = 2020,
- month = nov,
- doi = {10.1109/TPAMI.2020.3040591},
- url = {https://www.merl.com/publications/TR2021-029}
- }
, - "LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR42600.2020.00826, June 2020.BibTeX TR2020-067 PDF Video Data Software
- @inproceedings{Kumar2020jun,
- author = {Kumar, Abhinav and Marks, Tim and Mou, Wenxuan and Wang, Ye and Cherian, Anoop and Jones, Michael J. and Liu, Xiaoming and Koike-Akino, Toshiaki and Feng, Chen},
- title = {LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood},
- booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
- year = 2020,
- month = jun,
- publisher = {IEEE},
- doi = {10.1109/CVPR42600.2020.00826},
- issn = {2575-7075},
- isbn = {978-1-7281-7168-5},
- url = {https://www.merl.com/publications/TR2020-067}
- }
,
- "Perceptual Metric Learning for Video Anomaly Detection", Machine Vision and Applications, DOI: 0.1007/s00138-021-01187-5, Vol. 32, No. 63, March 2021.
-
Other Publications
- "Lfw results using a combined nowak plus merl recognizer", 2008.BibTeX
- @Article{huang2008lfw,
- author = {Huang, G.B. and Jones, M.J. and Learned-Miller, E. and others},
- title = {Lfw results using a combined nowak plus merl recognizer},
- year = 2008
- }
, - "Analogous view transfer for gaze correction in video sequences", Control, Automation, Robotics and Vision, 2002. ICARCV 2002. 7th International Conference on, 2002, vol. 3, pp. 1415-1420.BibTeX
- @Inproceedings{cham2002analogous,
- author = {Cham, T.J. and Krishnamoorthy, S. and Jones, M.},
- title = {Analogous view transfer for gaze correction in video sequences},
- booktitle = {Control, Automation, Robotics and Vision, 2002. ICARCV 2002. 7th International Conference on},
- year = 2002,
- volume = 3,
- pages = {1415--1420},
- organization = {IEEE}
- }
, - "Statistical color models with application to skin detection", International Journal of Computer Vision, Vol. 46, No. 1, pp. 81-96, 2002.BibTeX
- @Article{jones2002statistical,
- author = {Jones, M.J. and Rehg, J.M.},
- title = {Statistical color models with application to skin detection},
- journal = {International Journal of Computer Vision},
- year = 2002,
- volume = 46,
- number = 1,
- pages = {81--96},
- publisher = {Springer}
- }
, - "Appearance-based structure from motion using linear classes of 3-d models", International Journal of Computer Vision, Vol. 49, No. 1, pp. 5-22, 2002.BibTeX
- @Article{kang2002appearance,
- author = {Kang, S.B. and Jones, M.},
- title = {Appearance-based structure from motion using linear classes of 3-d models},
- journal = {International Journal of Computer Vision},
- year = 2002,
- volume = 49,
- number = 1,
- pages = {5--22},
- publisher = {Springer}
- }
, - "A Monte Carlo algorithm for fast projective clustering", Proceedings of the 2002 ACM SIGMOD international conference on Management of data, 2002, pp. 418-427.BibTeX
- @Inproceedings{procopiuc2002monte,
- author = {Procopiuc, C.M. and Jones, M. and Agarwal, P.K. and Murali, TM},
- title = {A Monte Carlo algorithm for fast projective clustering},
- booktitle = {Proceedings of the 2002 ACM SIGMOD international conference on Management of data},
- year = 2002,
- pages = {418--427},
- organization = {ACM}
- }
, - "Fast and robust classification using asymmetric adaboost and a detector cascade", Proc. of NIPS01, 2001.BibTeX
- @Article{viola2001fast,
- author = {Viola, P. and Jones, M.},
- title = {Fast and robust classification using asymmetric adaboost and a detector cascade},
- journal = {Proc. of NIPS01},
- year = 2001
- }
, - "Statistical color models with application to skin detection", Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., 1999, vol. 1.BibTeX
- @Inproceedings{jones1999statistical,
- author = {Jones, M.J. and Rehg, J.M.},
- title = {Statistical color models with application to skin detection},
- booktitle = {Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on.},
- year = 1999,
- volume = 1,
- organization = {IEEE}
- }
, - "A cluster-based statistical model for object detection", Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, 1999, vol. 2, pp. 1046-1053.BibTeX
- @Inproceedings{rikert1999cluster,
- author = {Rikert, T.D. and Jones, M.J. and Viola, P.},
- title = {A cluster-based statistical model for object detection},
- booktitle = {Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on},
- year = 1999,
- volume = 2,
- pages = {1046--1053},
- organization = {IEEE}
- }
, - "Hierarchical morphable models", Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on, 1998, pp. 820-826.BibTeX
- @Inproceedings{jones1998hierarchical,
- author = {Jones, M.J. and Poggio, T.},
- title = {Hierarchical morphable models},
- booktitle = {Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on},
- year = 1998,
- pages = {820--826},
- organization = {IEEE}
- }
, - "Multidimensional morphable models: A framework for representing and matching object classes", International Journal of Computer Vision, Vol. 29, No. 2, pp. 107-131, 1998.BibTeX
- @Article{jones1998multidimensional,
- author = {Jones, M.J. and Poggio, T.},
- title = {Multidimensional morphable models: A framework for representing and matching object classes},
- journal = {International Journal of Computer Vision},
- year = 1998,
- volume = 29,
- number = 2,
- pages = {107--131},
- publisher = {Springer}
- }
, - "Gaze estimation using morphable models", Automatic Face and Gesture Recognition, 1998. Proceedings. Third IEEE International Conference on, 1998, pp. 436-441.BibTeX
- @Inproceedings{rikert1998gaze,
- author = {Rikert, T.D. and Jones, M.J.},
- title = {Gaze estimation using morphable models},
- booktitle = {Automatic Face and Gesture Recognition, 1998. Proceedings. Third IEEE International Conference on},
- year = 1998,
- pages = {436--441},
- organization = {IEEE}
- }
, - "Multidimensional morphable models: A framework for representing and matching object classes", 1997.BibTeX
- @Phdthesis{jones1997multidimensional,
- author = {Jones, M.J.},
- title = {Multidimensional morphable models: A framework for representing and matching object classes},
- year = 1997,
- publisher = {Massachusetts Institute of Technology}
- }
, - "Top-down learning of low-level vision tasks", Current Biology, Vol. 7, No. 12, pp. 991-994, 1997.BibTeX
- @Article{jones1997top,
- author = {Jones, M.J. and Sinha, P. and Vetter, T. and Poggio, T.},
- title = {Top-down learning of low-level vision tasks},
- journal = {Current Biology},
- year = 1997,
- volume = 7,
- number = 12,
- pages = {991--994},
- publisher = {Elsevier}
- }
, - "A bootstrapping algorithm for learning linear models of object classes", Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on, 1997, pp. 40-46.BibTeX
- @Inproceedings{vetter1997bootstrapping,
- author = {Vetter, T. and Jones, M.J. and Poggio, T.},
- title = {A bootstrapping algorithm for learning linear models of object classes},
- booktitle = {Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on},
- year = 1997,
- pages = {40--46},
- organization = {IEEE}
- }
, - "Regularization theory and neural networks architectures", Neural computation, Vol. 7, No. 2, pp. 219-269, 1995.BibTeX
- @Article{girosi1995regularization,
- author = {Girosi, F. and Jones, M. and Poggio, T.},
- title = {Regularization theory and neural networks architectures},
- journal = {Neural computation},
- year = 1995,
- volume = 7,
- number = 2,
- pages = {219--269},
- publisher = {MIT Press}
- }
, - "Model-based matching of line drawings by linear combinations of prototypes", Computer Vision, 1995. Proceedings., Fifth International Conference on, 1995, pp. 531-536.BibTeX
- @Inproceedings{jones1995model,
- author = {Jones, M.J. and Poggio, T.},
- title = {Model-based matching of line drawings by linear combinations of prototypes},
- booktitle = {Computer Vision, 1995. Proceedings., Fifth International Conference on},
- year = 1995,
- pages = {531--536},
- organization = {IEEE}
- }
, - "Priors stabilizers and basis functions: From regularization to radial, tensor and additive splines", MIT AI Lab Memo 1430, 1993.BibTeX
- @Article{girosi1993priors,
- author = {Girosi, F. and Jones, M. and Poggio, T.},
- title = {Priors stabilizers and basis functions: From regularization to radial, tensor and additive splines},
- journal = {MIT AI Lab Memo 1430},
- year = 1993
- }
, - "From regularization to radial, tensor and additive splines", Neural Networks, 1993. IJCNN'93-Nagoya. Proceedings of 1993 International Joint Conference on, 1993, vol. 1, pp. 223-227.BibTeX
- @Inproceedings{poggio1993regularization,
- author = {Poggio, T. and Girosi, F. and Jones, M.},
- title = {From regularization to radial, tensor and additive splines},
- booktitle = {Neural Networks, 1993. IJCNN'93-Nagoya. Proceedings of 1993 International Joint Conference on},
- year = 1993,
- volume = 1,
- pages = {223--227},
- organization = {IEEE}
- }
, - "Using recurrent networks for dimensionality reduction", 1992, Massachusetts Institute of Technology.BibTeX
- @Mastersthesis{jones1992using,
- author = {Jones, M.J.},
- title = {Using recurrent networks for dimensionality reduction},
- school = {Massachusetts Institute of Technology},
- year = 1992
- }
,
- "Lfw results using a combined nowak plus merl recognizer", 2008.
-
Software Downloads
-
Videos
-
MERL Issued Patents
-
Title: "System and Method for Detecting Motion Anomalies in Video"
Inventors: Jones, Michael J.
Patent No.: 10,970,823
Issue Date: Apr 6, 2021 -
Title: "System and Method for Detecting Anomalies in Video using a Similarity Function Trained by Machine Learning"
Inventors: Jones, Michael J.
Patent No.: 10,824,935
Issue Date: Nov 3, 2020 -
Title: "Method and System for Determining 3D Object Poses and Landmark Points using Surface Patches"
Inventors: Jones, Michael J.; Marks, Tim; Papazov, Chavdar
Patent No.: 10,515,259
Issue Date: Dec 24, 2019 -
Title: "System and Method for Image Comparison Based on Hyperplanes Similarity"
Inventors: Jones, Michael J.
Patent No.: 10,452,958
Issue Date: Oct 22, 2019 -
Title: "Method and System for Detecting Actions in Videos"
Inventors: Jones, Michael J.; Tuzel, Oncel; Marks, Tim; Singh, Bharat
Patent No.: 10,242,266
Issue Date: Mar 26, 2019 -
Title: "Method and System for Detecting Actions in Videos using Contour Sequences"
Inventors: Jones, Michael J.; Marks, Tim; Kulkarni, Kuldeep
Patent No.: 10,210,391
Issue Date: Feb 19, 2019 -
Title: "Method for Anomaly Detection in Time Series Data Based on Spectral Partitioning"
Inventors: Nikovski, Daniel N.; Kniazev, Andrei; Jones, Michael J.
Patent No.: 9,984,334
Issue Date: May 29, 2018 -
Title: "Method for Learning Exemplars for Anomaly Detection"
Inventors: Jones, Michael J.; Nikovski, Daniel N.
Patent No.: 9,779,361
Issue Date: Oct 3, 2017 -
Title: "Method for Determining Similarity of Objects Represented in Images"
Inventors: Jones, Michael J.; Marks, Tim; Ahmed, Ejaz
Patent No.: 9,436,895
Issue Date: Sep 6, 2016 -
Title: "Method and System for Tracking People in Indoor Environments using a Visible Light Camera and a Low-Frame-Rate Infrared Sensor"
Inventors: Marks, Tim; Jones, Michael J.; Kumar, Suren
Patent No.: 9,245,196
Issue Date: Jan 26, 2016 -
Title: "Method for Detecting and Tracking Objects in Image Sequences of Scenes Acquired by a Stationary Camera"
Inventors: Marks, Tim; Jones, Michael J.; MV, Rohith
Patent No.: 9,213,896
Issue Date: Dec 15, 2015 -
Title: "Method for Detecting Anomalies in a Time Series Data with Trajectory and Stochastic Components"
Inventors: Jones, Michael J.
Patent No.: 9,146,800
Issue Date: Sep 29, 2015 -
Title: "Method for Predicting Future Travel Time Using Geospatial Inference"
Inventors: Jones, Michael J.; Nikovski, Daniel N.; Geng, Yanfeng
Patent No.: 9,122,987
Issue Date: Sep 1, 2015 -
Title: "Method for Detecting Anomalies in Multivariate Time Series Data"
Inventors: Nikovski, Daniel N.; Jones, Michael J.
Patent No.: 9,075,713
Issue Date: Jul 7, 2015 -
Title: "Camera-Based 3D Climate Control"
Inventors: Marks, Tim; Jones, Michael J.
Patent No.: 8,929,592
Issue Date: Jan 6, 2015 -
Title: "Object Detection in Depth Images"
Inventors: Jones, Michael J.; Tuzel, C. Oncel; Si, Weiguang
Patent No.: 8,406,470
Issue Date: Mar 26, 2013 -
Title: "Method for identifying Faces in Images with Improved Accuracy Using Compressed Feature Vectors"
Inventors: Thornton, Jay E.; Jones, Michael J.
Patent No.: 8,213,691
Issue Date: Jul 3, 2012 -
Title: "Method for Synthetically Images of Objects"
Inventors: Jones, Michael J.; Marks, Tim; Kumar, Ritwik
Patent No.: 8,194,072
Issue Date: Jun 5, 2012 -
Title: "Method for Localizing Irises in Images Using Gradients and Textures"
Inventors: Jones, Michael J.; Guo, Guo Dong
Patent No.: 7,583,823
Issue Date: Sep 1, 2009 -
Title: "Detecting Pedestrians Using Patterns of Motion and Appearance in Videos"
Inventors: Jones, Michael J.; Viola, Paul A.
Patent No.: 7,212,651
Issue Date: May 1, 2007 -
Title: "Detecting Arbitrarily Oriented Objects in Images"
Inventors: Viola, Paul A.; Jones, Michael J.
Patent No.: 7,197,186
Issue Date: Mar 27, 2007 -
Title: "Object Recognition System"
Inventors: Viola, Paul A.; Jones, Michael J.
Patent No.: 7,031,499
Issue Date: Apr 18, 2006 -
Title: "System and Method for Detecting Objects in Images"
Inventors: Viola, Paul A.; Jones, Michael J.
Patent No.: 7,020,337
Issue Date: Mar 28, 2006
-
Title: "System and Method for Detecting Motion Anomalies in Video"