Establishing correspondence between features of a set of images has been a long-standing issue amongst the computer vision community. We propose a method that solves the multi-frame correspondence problem by imposing a rank constraint on the observed scene, i.e. rigidity is assumed. Since our algorithm is based solely on a geometrical (global) criterion, it does not suffer from issues usually a...

Visual input is frequently disrupted by eye movements, blinks, and occlusion. The visual system must be able to establish correspondence between objects visible before and after a disruption. Current theories hold that correspondence is established solely on the basis of spatiotemporal information, with no contribution from surface features. In five experiments, we tested the relative contribut...

Due to physiology and linguistic difference between speakers, the spectrum pattern for the same phoneme of two speakers can be quite dissimilar. Without appropriate alignment on the frequency axis, the misalignment will reduce the modeling efficiency resutling in performance degradation. In this paper, a novel data-driven framework is proposed to build the alignment of the frequency axes of two...

Matching feature point sets lies at the core of many approaches to object recognition. We present a framework for non-rigid matching that begins with a skeleton module, affine point matching, and then integrates multiple features to improve correspondence and develops an object representation based on spatial regions to model local transformations. The algorithm for feature matching iteratively...

We examined how stream/bounce event perception is affected by motion correspondence based on the surface features of moving objects passing behind an occlusion. In the stream/bounce display two identical objects moving across each other in a two-dimensional display can be perceived as either streaming through or bouncing off each other at coincidence. Here, surface features such as colour (Expe...

Statistical analysis of shape representations relies on having good correspondence across a population. Improving correspondence yields improved statistics. Point distribution models (PDMs) are often used to represent object boundaries. Skeletal representations (s-reps) model object widths and boundary directions as well as boundary positions, so they should yield better correspondence. We pres...

Visualization of time-dependent data is an enormous task because of the immense amount of data involved. However, most of the time the scientist is mainly interested in the evolution of certain features. Therefore, it suffices to show the evolution of these features. The task of the visualization system is to extract the features from all frames, to determine the correspondences between feature...

Most existing feature-point matching algorithms rely on photometric region descriptors to distinct and match feature points in two images. In this paper, we propose an efficient feature-point matching algorithm for finding point correspondences between two uncalibrated images separated by small or mid camera baselines. The proposed algorithm does not rely on photometric descriptors for matching...

Robust online multi-person tracking requires the correct associations of online detection responses with existing trajectories. We address this problem by developing a novel appearance modeling approach to provide accurate appearance affinities to guide data association. In contrast to most existing algorithms that only consider the spatial structure of human appearances, we exploit the tempora...

We extend the Structural Correspondence Learning (SCL) domain adaptation algorithm of Blitzer et al. [4] to the realm of continuous signals. Given a set of labeled examples belonging to a “source” domain, we select a set of unlabeled examples in a related “target” domain that play similar roles in both domains. Using these “pivot samples,” we map both domains into a common feature space, allowi...