Sciweavers

606 search results - page 99 / 122
» Capturing the Intention of Model Changes
Sort
View
CVPR
2006
IEEE
15 years 2 days ago
A Generative-Discriminative Hybrid Method for Multi-View Object Detection
We present a novel discriminative-generative hybrid approach in this paper, with emphasis on application in multiview object detection. Our method includes a novel generative mode...
DongQing Zhang, Shih-Fu Chang
ICCV
2007
IEEE
15 years 16 hour ago
Evaluation of Large Scale Scene Reconstruction
We present an evaluation methodology and data for large scale video-based 3D reconstruction. We evaluate the effects of several parameters and draw conclusions that can be useful ...
Paul Merrell, Philippos Mordohai, Jan-Michael Frah...
ICCV
2007
IEEE
15 years 16 hour ago
A Layer-Based Restoration Framework for Variable-Aperture Photography
We present variable-aperture photography, a new method for analyzing sets of images captured with different aperture settings, with all other camera parameters fixed. We show that...
Samuel W. Hasinoff, Kiriakos N. Kutulakos
ECCV
2004
Springer
14 years 12 months ago
Estimating Intrinsic Images from Image Sequences with Biased Illumination
We present a method for estimating intrinsic images from a fixed-viewpoint image sequence captured under changing illumination directions. Previous work on this problem reduces the...
Yasuyuki Matsushita, Stephen Lin, Sing Bing Kang, ...
ICPR
2002
IEEE
14 years 11 months ago
Quasi-Invariants for Human Action Representation and Recognition
Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an ...
Vasu Parameswaran, Rama Chellappa