Associate Professor
Computer Science and Engineering
SUNY at Buffalo
Jason J. Corso
| Email: | jcorso@buffalo.edu |
| Office: | Davis Hall 332 |
| Phone: | 716-645-4754 |
| Bio: | [txt] |
| Vita: | [pdf] |
| Hours: | TR 12:30-2:00 by appointment |
| Cal: | Availability |
| Job Openings | |
Publication Tag Cloud
active clustering activity recognition artificial intelligence augmented reality belief propagation bioinformatics biomarkers biometrics braintumor computational finance computer forensics computer graphics computer vision computer-aided diagnosis cosegmentation data mining deformable dictionary transfer document imaging domain adaptation dynamic linear models endoscopy evaluation event recognition facade detection face detection face recognition feature extraction fusion gesture recognition gpu grammar graph cuts graph-based graphical models haptics hierarchical higher-order human pose estimation human-computer interaction image denoising image processing image retrieval image understanding localization lung imaging machine learning mapping max-margin medical imaging metric learning mobile robotics mosaicking motion estimation mrf multimedia natural language navigation neuroimaging object detection ontology probabilistic ontology protein structure prediction random forest reconstruction segmentation semantic segmentation slam spectral clustering spine imaging stereo streaming supervoxel surgical robotics tomographic reconstruction tracking video summarization video understanding volume rendering voxel maps
Dr. Jason J. Corso is currently 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 imaging 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?
|
Selected Publications
[complete list here]
Code and Data Downloads
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.
Random Forest Distance -- tree-structured metric learning that implicitly adapts the metric over the sample space based on our KDD 2012 paper.
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].
Professional Service
CSE 555: Introduction to Pattern Recognition -- Spring 2009--2013
CSE 672: Bayesian Vision -- Spring 2008, Fall 2010, Fall 2012 CSE 642: Techniques in AI: Vision for HCI -- Fall 2009 CSE 702: Seminar in Image Semantics -- Fall 2009 CSE 702: Seminar in Pattern Theory -- Fall 2008 CSE 702: Seminar: Topics in Medical Image Segmentation -- Fall 2007 Miscellaneous
|
News and Events
|
