Jason J. Corso
Publication Tag Cloud
|
Dr. Jason J. Corso is currently [was] an associate professor of Computer
Science and Engineering Department at SUNY at Buffalo.He
received his Ph.D. in Computer Science at The Johns Hopkins University in
2005. He received the M.S.E Degree from The Johns Hopkins University in
2002 and the B.S. Degree with honors from Loyola College In Maryland in
2000, both in Computer Science. He spent two years as a post-doctoral
research fellow at the University of California, Los Angeles. He is a
recipient of the NSF CAREER award, ARO Young Investigator award, on the DARPA
CSSG, UB Young Investigator award and a UB Innovator
award.
His main research thrust is high-level computer vision and data science,
primarily focusing on problems in video understanding such as video
segmentation, activity recognition, and video-to-text. From biomedicine to
recreational video, imaging data is ubiquitous. Yet, imaging scientists and
intelligence analysts are without an adequate language and set of tools to
fully tap the information-rich image and video. He works to provide such a
language; specifically, he studies the coupled problems of segmentation and
recognition from a Bayesian perspective emphasizing the role of statistical
models in efficient visual inference. His long-term goal is a
comprehensive and robust methodology of automatically mining, quantifying, and
generalizing information in large sets of projective and volumetric images and
video. The following four questions drive his current research inquiries:
- How to use principled hierarchical structures to model complex real-world phenomena?
- How to handle the massive data glut for machine learning while appropriately incorporating the user and yet requiring little labeling?
- How to incorporate prior high-level knowledge (semantics, ontology, context, etc.) during both learning and inference?
- What is the relationship between vision and language and action and reasoning?
More broadly, his research interests are in the fields of computer vision, robot perception, data sciences and medical imaging. More information on these topics can be found in the research pages.
[1]
|
C. Xiong, S. McCloskey, and J. J. Corso.
Latent domains for visual domain adaptation.
In Proceedings of AAAI Conference on Artificial Intelligence,
2014.
[ bib ]
|
[2]
|
S. Kumar, V. Dhiman, and J. J. Corso.
Learning compositional sparse models of bimodal percepts.
In Proceedings of AAAI Conference on Artificial Intelligence,
2014.
[ bib |
code |
.pdf ]
|
[3]
|
W. Chen, C. Xiong, R. Xu, and J. J. Corso.
Actionness ranking with lattice conditional ordinal random fields.
In Proceedings of IEEE Conference on Computer Vision and
Pattern Recognition, 2014.
[ bib ]
|
[4]
|
V. Dhiman, A. Kundu, F. Dellaert, and J. J. Corso.
Modern MAP inference methods for accurate and faster occupancy grid
mapping on higher order factor graphs.
In Proceedings of International Conference on Robotics and
Automation, 2014.
[ bib |
code |
.pdf ]
|
[5]
|
C. Xiong, W. Chen, G. Chen, D. Johnson, and J. J. Corso.
Adaptive quantization: An information-based approach to learning
binary codes.
In Proceedings of SIAM International Conference on Data
Mining, 2014.
[ bib |
code |
.pdf ]
|
[6]
|
C. Xu, R. F. Doell, S. J. Hanson, C. Hanson, and J. J Corso.
A study of actor and action semantic retention in video supervoxel
segmentation.
International Journal of Semantic Computing, 2014.
(In Press) Selected as a Best Paper from ICSC; an earlier version
appeared as arXiv:1311.3318.
[ bib |
.pdf ]
|
[7]
|
C. Xu, S. Whitt, and J. J. Corso.
Flattening supervoxel hierarchies by the uniform entropy slice.
In Proceedings of the IEEE International Conference on Computer
Vision, 2013.
[ bib |
poster |
project |
video |
.pdf ]
|
[8]
|
V. Dhiman, J. Ryde, and J. J. Corso.
Mutual localization: Two camera relative 6-dof pose estimation from
reciprocal fiducial observation.
In Proceedings of International Conference on Intelligent Robots
and Systems, 2013.
[ bib |
slides |
code |
.pdf ]
|
[9]
|
L. Zhao, W. Wu, and J. J. Corso.
Semi-automatic brain tumor segmentation by constrained MRFs using
structural trajectories.
In Proceedings of Medical Image Computing and Computer Aided
Intervention, 2013.
[ bib |
.pdf ]
|
[10]
|
P. Das, C. Xu, R. F. Doell, and J. J. Corso.
A thousand frames in just a few words: Lingual description of videos
through latent topics and sparse object stitching.
In Proceedings of IEEE Conference on Computer Vision and
Pattern Recognition, 2013.
[ bib |
poster |
data |
.pdf ]
|
[11]
|
P. Das, R. K. Srihari, and J. J. Corso.
Translating related words to videos and back through latent topics.
In Proceedings of Sixth ACM International Conference on Web
Search and Data Mining, 2013.
[ bib |
.pdf ]
|
[12]
|
C. Xu, C. Xiong, and J. J. Corso.
Streaming hierarchical video segmentation.
In Proceedings of European Conference on Computer Vision, 2012.
[ bib |
code |
project |
.pdf ]
|
[13]
|
C. Xiong, D. Johnson, R. Xu, and J. J. Corso.
Random forests for metric learning with implicit pairwise position
dependence.
In Proceedings of ACM SIGKDD International Conference on
Knowledge Discovery and Data Mining, 2012.
[ bib |
slides |
code |
.pdf ]
|
[14]
|
S. Sadanand and J. J. Corso.
Action bank: A high-level representation of activity in video.
In Proceedings of IEEE Conference on Computer Vision and
Pattern Recognition, 2012.
[ bib |
code |
project |
.pdf ]
|
[15]
|
J. J. Corso, E. Sharon, S. Dube, S. El-Saden, U. Sinha, and
A. Yuille.
Efficient Multilevel Brain Tumor Segmentation with Integrated
Bayesian Model Classification.
IEEE Transactions on Medical Imaging, 27(5):629-640, 2008.
[ bib |
.pdf ]
|
Code and Data Downloads
Video2Text.net:
A website and web-service for automatic conversion of videos to natural
language sentences based on the video content. This website showcases our work
in the vision+language domain.
YouCook data set: 88 challenging
videos of various cooking (third-person viewpoint, different
backgrounds, dynamic camera and person movement) with natural
language annotations (about 8 per video) and object and action
annotations. Includes a benchmark ROUGE scoring evaluation. The
data set was published with our CVPR
2013 paper.
Hierarchy
Agreement Index: implementation of our AAAI LBP
2013 cross-hierarchy evaluation tool for general use.
Random Forest Distance -- tree-structured metric learning that implicitly adapts the metric over the sample space based on our KDD 2012 paper. (Code updated 2/28/14)
Action Bank full code and processed data sets [direct link to code]
LIBSVX: A Supervoxel Library and Benchmark for Early Video Processing. Implements a suite of supervoxel video segmentation methods as well as a quantitative set of 2D and 3D metrics for good supervoxels.
Graph-Shifts Code (Java)
and
example data.
Video label propagation code and benchmark data set.
UB/College Park stereo building facade dataset. [ more information].
ARO YIP (PI): GBS: Guidance By Semantics-Using High-Level
Visual Inference to Improve Vision-based Mobile Robot
Localization
DARPA MINDSEYE (PI): ISTARE: Intelligent Spatio-Temporal Activity Reasoning Engine
DARPA CSSG-III (PI): Transferring ACE to the Analyst
FHWA (CUBRC Sub) (PI): Computer Vision and Mobile Robot
Technologies for Advanced Emergency Response
IARPA ALADDIN (Kitware Sub) (PI): Ontology, Event Agents and Event
Recounting for ALADDIN
NIH (HRI Sub) (PI): Objective Imaging-Based Assessment of Smoking
Behavior from Used Filters
NSF CAREER (PI): CAREER: Generalized Image Understanding with Probabilistic Ontologies and Dynamic Adaptive Graph Hierarchies
Recently Expired Grants
DARPA CSSG-II (PI): ACE -- Active Clustering for Exploitation and Defense Forensics
Naval PS (PI): Comprehensive Object Detection Library for
Large-Scale Image Analytics
ARO DURIP (PI): Two-Rank Mobile Robot Fleet for Swarm
Surveillance, WarFighter Assistance, and other Army-related
Research and Research-Related Education
CIA (PI): Semantic Video
Summarization With Ontology-Driven Probabilistic Inference on
Massive Multimedia Collections
Professional Service
Associate Editor: Computer Methods and Programs in Biomedicine 2009-Currently
Area Chair: CVPR 2012 CVPR 2013, WACV 2014, ECCV 2014
Program Committee/Reviewer:
CVPR 2003 2006 2007 2009 2010 2011
ECCV 2006 2010
EMMCVPR 2007 2009 2011 2013
ICCV 2007 2009 2013
ICRA 2005 2009 2011 2012 2013
IROS 2007 2012; 2013
MICCAI 2003, 2006 2007 2008 2009 2012 2013
Miscellaneous
|
|
News and Events
This list is maintained via Twitter: . [Older pre-twitter news.]
|
|