ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
In contrast to traditional Markov random field (MRF) models, we develop a Steerable Random Field (SRF) in which the field potentials are defined in terms of filter responses that ...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. Cu...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
We introduce a novel topological formulation for contour grouping. Our grouping criterion, called untangling cycles, exploits the inherent topological 1D structure of salient cont...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
In this paper, we propose a novel approach for scene modeling. The proposed method is able to automatically discover the intermediate semantic concepts. We utilize Maximization of...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
We present a novel method to reconstruct the 3D shape of a scene from several calibrated images. Our motivation is that most existing multi-view stereovision approaches require so...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively ...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
Illumination changes cause object appearance to change drastically and many existing tracking algorithms lack the capability to handle this problem. The Earth Mover's Distanc...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
Learning-based superresolution (SR) are popular SR techniques that use application dependent priors to infer the missing details in low resolution images (LRIs). However, their pe...
ICCV
2007
IEEE
15 years 2 months ago
2007
IEEE
Real-world actions occur often in crowded, dynamic environments. This poses a difficult challenge for current approaches to video event detection because it is difficult to segmen...