Computer vision publications
-
Pose-Encoded Spherical Harmonics for Face Recognition and Synthesis Using a Single Image
In this paper, we propose to address one of the most challenging scenarios in face recognition. That is, to identify a subject from a test image that is acquired under…
-
Fostering Collaboration with a Semantic Index over Textual Contributions
We are exploring new approaches to facilitating effective collaboration that remove or reduce common barriers and that exploit opportunities to encourage more effective collaboration, including transcending the cognitive biases of…
-
PHERL: an Emerging Representation Language for Patterns, Hypotheses, and Evidence
We are developing PHERL, an interchange language for link analysis tools, which is designed to support the sharing of patterns and hypotheses (e.g., pattern-match results).
-
Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov model
We introduce the Switching Hidden Semi-Markov Model (S-HSMM), a two-layered extension of the hidden semi-Markov model (HSMM) for the modeling task.
-
A Knowledge Acquisition Tool for Course of Action Analysis
-
SRI’s Digital Earth Project
The goal of SRI International’s Digital Earth project was to develop the infrastructure for an open, distributed, multiresolution, 3-D representation of the earth, into which massive quantities of georeferenced information…
-
Lightweight solutions for user interfaces over the WWW
We present some lightweight tools that have been essential in producing applications with complex interactive interfaces.
-
Detecting Changes in 3-d Shape using Self-Consistency
A novel image-matching measure based on Minimum Description Length (MDL) theory allows us to estimate the accuracy of individual elements of the 3- D model. Experiments to demonstrate the utility…
-
Self-Consistency, A Novel Approach to Characterizing the Accuracy and Reliability of Point-Correspondence Algorithms
We present a framework for reliably and robustly detecting changes in terrain (or other 3-D objects) over time.
-
A Framework for Detecting Changes in Terrain
We propose a methodology that estimates the accuracy and reliability of the results of any multiple-image point correspondence algorithm, without the need for ground truth or camera calibration.
-
Using Differential Constraints to Reconstruct Complex Surfaces from Stereo
Stereo reconstruction algorithms often fail to properly deal with complex surfaces, because there is not enough image information. We propose to guide the reconstruction process using a priori information about…
-
Object-Centered Surface Reconstruction: Combining Multi-Image Stereo and Shading
We argue that an object-centered representation is most appropriate for this purpose becasue it naturally accomodates multiple sources of data, multiple images (including motion sequences of a rigid object), and…