| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 06 Oct 2021 16:20:46 GMT
access-control-allow-origin: *
etag: W/"615dccde-75d5"
expires: Tue, 30 Dec 2025 18:14:35 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 5F92:3ABDEF:A530DD:B9946C:69541432
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 18:04:35 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210078-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767117876.750785,VS0,VE206
vary: Accept-Encoding
x-fastly-request-id: 441cd6289cb2794b6c7d4c34ede6319b0961646b
content-length: 7674
I currently work at Google doing Machine Learning and Computer Vision research. I've worked on the Image Search and Photo Search teams. Before that, I obtained my Ph.D. from the Computer and Information Science department at the University of Pennsylvania. I worked with my advisor Ben Taskar solving computer vision problems with machine learning. Most of my work has been in using graphical models to solve human pose estimation in 2D images or video. Specifically, we study how to overcome computational bottlenecks that handicap most models applied to this problem, allowing us to design more expressive models with richer features that do better.
Bio:
San Diego, CA --> Bay Area --> Champaign-Urbana, IL --> Stanford, CA --> Princeton, NJ --> Philadelphia, PA --> San Francisco, CA --> Los Angeles, CA
Google Scholar page
Microsoft Academic page
Benjamin John Sapp, Ph.D.Computer and Information Science University of Pennsylvania / Google bensapp@google.com |
News
- I joined
in Mountain View, CA in December, 2012. - Thesis stuff up on publications page.
- MODEC code released.
- Results from CVPR11 paper Stretchable Models: https://www.youtube.com/watch?v=vnOh8_D3RhQ
- Soccer! I organize an informal recreational soccer pickup group for Penn grad students. Come one, come all. Subscribe to the mailing list: https://groups.google.com/group/penn-pickup-soccer. Also, I made an easy-to-read calendar which shows what Penn fields are free (unreserved).
- Parsing Human Motion with Stretchable Models code is out.
- I'm teaching Intelligent Game Agents this Fall 2012, along with Jenny and David.
About
I currently work at Google doing Machine Learning and Computer Vision research. I've worked on the Image Search and Photo Search teams. Before that, I obtained my Ph.D. from the Computer and Information Science department at the University of Pennsylvania. I worked with my advisor Ben Taskar solving computer vision problems with machine learning. Most of my work has been in using graphical models to solve human pose estimation in 2D images or video. Specifically, we study how to overcome computational bottlenecks that handicap most models applied to this problem, allowing us to design more expressive models with richer features that do better.
Bio:
San Diego, CA --> Bay Area --> Champaign-Urbana, IL --> Stanford, CA --> Princeton, NJ --> Philadelphia, PA --> San Francisco, CA --> Los Angeles, CA
Publications
Google Scholar page
Microsoft Academic page
Refereed conferences and journals
Thesis: Efficient Human Pose Estimation with Image-dependent
Interactions
Benjamin Sapp
University of Pennsylvania, 2012 @inproceedings{sapp-thesis,
author = "Benjamin Sapp",
title = "Efficient Human Pose Estimation with Image-dependent Interactions",
year = "2012"
}
| |
@inproceedings{modec13,
author = "Benjamin Sapp and Ben Taskar",
title = "MODEC",
booktitle = "CVPR",
year = "2013"
}
| |
Practicality of Accelerometer Side-Channel on Smartphones
Adam J. Aviv,
Ben Sapp,
Matt Blaze, and
Jonathan M. SmithACSAC 2012
paper
| bibtex
@inproceedings{aviv2012acsac,
author = "Adam J. Aviv and Benjamin Sapp and Matt Blaze and Jonathan M. Smith",
title = "Practicality of Accelerometer Side-Channel on Smartphones",
booktitle = "ACSAC",
year = "2012"
}
| |
Parsing Human Motion with Stretchable Models (oral)
Benjamin Sapp,
David Weiss and
Ben Taskar
CVPR 2011 @inproceedings{sapp2011cvpr,
author = "Benjamin Sapp and David Weiss and Ben Taskar",
title = "Parsing Human Motion with Stretchable Models",
booktitle = "CVPR",
year = "2011"
}
| |
@article{cour2011jmlr,
author = "Timothee Cour and Benjamin Sapp and Ben Taskar",
title = "Learning from Partial Labels",
journal = "JMLR",
year = "2011"
}
| |
|
Sidestepping Intractable Inference with Structured Ensemble Cascades
@inproceedings{sapp2010nips,
author = "Benjamin Sapp and David Weiss and Ben Taskar",
title = "Sidestepping Intractable Inference with Structured Ensemble Cascades.",
booktitle = "NIPS",
year = "2010"
}
| |
|
Cascaded Models for Articulated Pose Estimation (oral)
Benjamin Sapp,
Alexander Toshev and
Ben Taskar
ECCV 2010 @inproceedings{sapp2010eccv,
author = "Benjamin Sapp and Alexander Toshev and Ben Taskar",
title = "Cascaded Models for Articulated Pose Estimation.",
booktitle = "ECCV",
year = "2010"
}
| |
@inproceedings{sapp2010,
author = "Benjamin Sapp and Chris Jordan and Ben Taskar",
title = "Adaptive Pose Priors for Pictorial Structures",
booktitle = "CVPR",
year = "2010"
}
| |
|
Talking Pictures: Temporal Grouping and Dialog-Supervised Person Recognition
Timothee Cour,
Benjamin Sapp,
Akash Nagle
and Ben Taskar
CVPR 2010 @inproceedings{cour2010,
author = "Timothee Cour and Benjamin Sapp and Akash Nagle and Ben Taskar",
title = "Talking Pictures: Temporal Grouping and Dialog-Supervised Person Recognition",
booktitle = "CVPR",
year = "2010"
}
| |
|
Learning From Ambiguously Labeled Images
Timothee Cour,
Benjamin Sapp,
Chris Jordan and
Ben Taskar
CVPR 2009 @inproceedings{cour2009,
author = "Timothee Cour and Benjamin Sapp and Chris Jordan and Ben Taskar",
title = "Learning from Ambiguously Labeled Images",
booktitle = "CVPR",
year = "2009"
}
| |
|
A Fast Data Collection and Augmentation Procedure for Object Recognition
Benjamin Sapp,
Ashutosh Saxena
and Andrew Y. Ng
AAAI 2008 @inproceedings{sapp2008,
author = {Sapp, Benjamin and Saxena, Ashutosh and Ng, Andrew Y.},
title = {A fast data collection and augmentation procedure for object recognition},
booktitle = {AAAI},
year = {2008},
isbn = {978-1-57735-368-3},
pages = {1402--1408},
location = {Chicago, Illinois},
publisher = {AAAI Press},
}
| |
|
Peripheral-Foveal Vision for Real-time Object Recognition and Tracking in Video
Stephen Gould,
Joakim Arfvidsson,
Adrian Kaehler,
Benjamin Sapp,
Marius Meissner,
Gary Bradski,
Paul Baumstarck,
Sukwon Chung and
Andrew Y. Ng
IJCAI 2007 @inproceedings{gould2007,
author = {Gould, Stephen and Arfvidsson, Joakim and Kaehler, Adrian and
Sapp, Benjamin and Messner, Marius and
Bradski, Gary and Baumstarck, Paul and Chung, Sukwon and Ng, Andrew Y.},
title = {Peripheral-foveal vision
for real-time object recognition and tracking in video},
booktitle = {IJCAI07},
year = {2007},
pages = {2115--2121},
location = {Hyderabad, India},
publisher = {Morgan Kaufmann Publishers Inc.},
address = {San Francisco, CA, USA},
}
|
Workshops, tech reports, patents, &c.
|
Recognizing Manipulation Actions in Arts and Crafts Shows using Domain-Specific Visual and Textual Cues
B. Sapp, R. Chaudhry, X. Yu, G. Singh, I. Perera, F. Ferraro, E. Tzoukermann, J. Kosecka, J. Neumann
ICCV VECTaR Workshop. November 2011. | |
|
Language Models for Semantic Extraction and Filtering in Video Action Recognition
Tzoukermann E., J. Neumann, J. Kosecka, C. Fermuller, I. Perera, F. Ferraro, B. Sapp, R. Chaudhry and G. Singh
AAAI Workshop on Language-Action Tools for Cognitive Artificial Agents. August 2011 | |
|
Randomized Algorithms for Low-Rank Matrix Decomposition
Benjamin Sapp
Written Preliminary Examination II. May 2011 | |
|
Learning From Ambiguously Labeled Images
Timothee Cour,
Benjamin Sapp,
Chris Jordan and
Ben Taskar
Technical Report MS-CIS-09-07, University of Pennsylvania. May 2009 @techreport{cour2009,
author = "Timothee Cour and Benjamin Sapp and Chris Jordan and Ben Taskar",
title = "Learning from Ambiguously Labeled Images",
institution = "University of Pennsylvania, Department of Computer and Information Science",
year = "2009"
}
| |
|
Method and System for Detection of Contrast Injection in Fluoroscopic Image Sequences
Benjamin Sapp, Wei Zhang, Bogdan Georgescu, Simone Prummer and Dorin Comaniciu
US Patent US12/231,770. September 2008 | |
|
Peripheral-Foveal Vision for Real-time Object Recognition and Tracking in Video: Live Demonstration
Stephen Gould,
Benjamin Sapp,
Morgan Quigley,
Andrew Y. Ng.
NIPS 2006 | |
|
Robot Modeling and Control
M. Spong, S. Hutchinson, M. Vidyasagar, John Wiley and Sons, New York, 2006.
Acknowledgement for experiments used in Chapter 11. |
- Curriculum Vitæ pdf (last updated 3/23/2012)
- Co-organizer for the Coarse-to-Fine Learning and Inference NIPS 2010 workshop.
- Reviewer for:
- JMLR11, PAMI11, IJCV12
- NIPS{08,09,10,11}, IJCAI09, AISTATS11, CVPR{11,12}, ICML11, ECCV{10,12}, ICCV11, WiML10
-
Summers spent at:
- JHU Center for Language and Speech Processing research workshop, 2010, Baltimore, MD, with Jan Neumann and Jana Kosecka.
- Siemens Coroporate Research, 2007, Princeton, NJ, with Dorin Comaniciu and Adrian Barbu.
- Intel, 2006, Santa Clara, CA, with Gary Bradski.
|
Ben Sapp benjamin.sapp@gmail.com Current work address: 1600 Amphitheatre Pkwy Mountain View, CA 94043 |



