Raghuraman Gopalan

Learn More
Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we present one of the first studies on unsupervised domain adaptation in the context of object recognition, where we have labeled data only from the source domain (and therefore do not(More)
Given a set of points corresponding to a 2D projection of a non-planar shape, we would like to obtain a representation invariant to articulations (under no self-occlusions). It is a challenging problem since we need to account for the changes in 2D shape due to 3D articulations, viewpoint variations, as well as the varying effects of imaging process on(More)
With unconstrained data acquisition scenarios widely prevalent, the ability to handle changes in data distribution across training and testing data sets becomes important. One way to approach this problem is through domain adaptation, and in this paper we primarily focus on the unsupervised scenario where the labeled source domain training data is(More)
14. Related to our representation: 15. R̃ the shape representation we are interested in (Equation 1) 16. D the distance that is preserved under non-planar articulations, upto a data-dependent error (Equation 2) 17. 2? error terms (Equation 5) 18. T the transformation to perform part-wise affine normalization 19. hlk histogram of a point ul ∈ Sk; R̃ is built(More)
In pattern recognition and computer vision, one is often faced with scenarios where the training data used to learn a model have different distribution from the data on which the model is applied. Regardless of the cause, any distributional change that occurs after learning a classifier can degrade its performance at test time. Domain adaptation tries to(More)
Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition by a fusion of image-formation models and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then, under certain assumptions, provide a differential(More)
1077-3142/$ see front matter 2009 Elsevier Inc. A doi:10.1016/j.cviu.2009.07.005 * Corresponding author. E-mail addresses: raghuram@umiacs.umd.edu (R umd.edu (D. Jacobs). Face recognition under changing lighting conditions is a challenging problem in computer vision. In this paper, we analyze the relative strengths of different lighting insensitive(More)
Road scene analysis is a challenging problem that has applications in autonomous navigation of vehicles. An integral component of this system is the robust detection and tracking of lane markings. It is a hard problem primarily due to large appearance variations in lane markings caused by factors such as occlusion (traffic on the road), shadows (from(More)
The challenging problem of planning manipulation tasks for dexterous robotic hands can be significantly simplified if the robot system has the ability to learn manipulation skills by observing a human demonstrator. Toward this goal, we present a novel computer vision based hand posture recognition system to serve as an intelligent interface for skill(More)
Estimating geographic location from images is a challenging problem that is receiving recent attention. In contrast to many existing methods that primarily model discriminative information corresponding to different locations, we propose joint learning of information that images across locations share and vary upon. Starting with generative and(More)