Search For:

Displaying 1-7 out of 7 total
Domain adaptive object detection
Found in: 2013 IEEE Workshop on Applications of Computer Vision (WACV)
By Fatemeh Mirrashed,Vlad I. Morariu,Behjat Siddiquie,Rogerio S. Feris,Larry S. Davis
Issue Date:January 2013
pp. 323-330
We study the use of domain adaptation and transfer learning techniques as part of a framework for adaptive object detection. Unlike recent applications of domain adaptation work in computer vision, which generally focus on image classification, we explore ...
Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance
Found in: Computer Vision, IEEE International Conference on
By Ryan Farrell,Om Oza, Ning Zhang,Vlad I. Morariu,Trevor Darrell,Larry S. Davis
Issue Date:November 2011
pp. 161-168
Subordinate-level categorization typically rests on establishing salient distinctions between part-level characteristics of objects, in contrast to basic-level categorization, where the presence or absence of parts is determinative. We develop an approach ...
Modeling Correspondences for Multi-Camera Tracking Using Nonlinear Manifold Learning and Target Dynamics
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Vlad I. Morariu, Octavia I. Camps
Issue Date:June 2006
pp. 545-552
Multi-camera tracking systems often must maintain consistent identity labels of the targets across views to recover 3D trajectories and fully take advantage of the additional information available from the multiple sensors. Previous approaches to the
Dynamic Appearance Modeling for Human Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hwasup Lim, Octavia I. Camps, Mario Sznaier, Vlad I. Morariu
Issue Date:June 2006
pp. 751-757
Dynamic appearance is one of the most important cues for tracking and identifying moving people. However, direct modeling spatio-temporal variations of such appearance is often a difficult problem due to their high dimensionality and nonlinearities. In thi...
Composite Discriminant Factor analysis
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Vlad I. Morariu,Ejaz Ahmed,Venkataraman Santhanam,David Harwood,Larry S. Davis
Issue Date:March 2014
pp. 564-571
We propose a linear dimensionality reduction method, Composite Discriminant Factor (CDF) analysis, which searches for a discriminative but compact feature subspace that can be used as input to classifiers that suffer from problems such as multi-collinearit...
Interactive video segmentation using occlusion boundaries and temporally coherent superpixels
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Radu Dondera,Vlad Morariu, Yulu Wang,Larry Davis
Issue Date:March 2014
pp. 784-791
We propose an interactive video segmentation system built on the basis of occlusion and long term spatio-temporal structure cues. User supervision is incorporated in a superpixel graph clustering framework that differs crucially from prior art in that it m...
Using vision, acoustics, and natural language for disambiguation
Found in: Proceeding of the ACM/IEEE international conference on Human-robot interaction (HRI '07)
By Alan Schultz, Benjamin Fransen, Dennis Perzanowski, Eric Martinson, Matthew Marge, Samuel Blisard, Scott Thomas, Vlad Morariu
Issue Date:March 2007
pp. 73-80
Creating a human-robot interface is a daunting experience. Capabilities and functionalities of the interface are dependent on the robustness of many different sensor and input modalities. For example, object recognition poses problems for state-of-the-art ...