Sciweavers

CVPR
2010
IEEE
14 years 2 months ago
Quasi-Dense 3D Reconstruction using Tensor-based Multiview Stereo
We propose tensor-based multiview stereo (TMVS) for quasi-dense 3D reconstruction from uncalibrated images. Our work is inspired by the patch-based multiview stereo (PMVS), a stat...
Tai-Pang Wu, Sai-Kit Yeung, Jiaya Jia, Chi-keung T...
CVPR
2010
IEEE
14 years 2 months ago
Pushing the Envelope of Modern Methods for Bundle Adjustment
In this paper, we present results and experiments with several methods for bundle adjustment, producing the fastest bundle adjuster ever published. The fastest methods work with t...
Yekeun Jeong, David Nister, Drew Steedly, Richard ...
CVPR
2010
IEEE
14 years 2 months ago
Neuron Geometry Extraction by Perceptual Grouping in ssTEM images
In the field of neuroanatomy, automatic segmentation of electron microscopy images is becoming one of the main limiting factors in getting new insights into the functional struct...
Verena Kaynig, Thomas Fuchs, Joachim Buhmann
CVPR
2010
IEEE
14 years 2 months ago
Multiple Object Detection by Sequential Monte Carlo and Hierarchical Detection Network
Michal Sofka, Jingdan Zhang, Kevin Zhou, Comaniciu...
CVPR
2010
IEEE
14 years 2 months ago
Multi-Target Tracking by On-Line Learned Discriminative Appearance Models
We present an approach for online learning of discriminative appearance models for robust multi-target tracking in a crowded scene from a single camera. Although much progress has...
Cheng-Hao Kuo, Chang Huang, Ram Nevatia
CVPR
2010
IEEE
14 years 2 months ago
Many-to-one Contour Matching for Describing and Discriminating Object Shape
We present an object recognition system that locates an object, identifies its parts, and segments out its contours. A key distinction of our approach is that we use long, salien...
Praveen Srinivasan, Qihui Zhu, Jianbo Shi
CVPR
2010
IEEE
14 years 2 months ago
Line Matching Leveraged By Point Correspondences
A novel method for line matching is proposed. The basic idea is to use tentative point correspondences, which can be easily obtained by keypoint matching methods, to significantly...
Bin Fan, Fuchao Wu, Zhanyi Hu
CVPR
2010
IEEE
14 years 2 months ago
Learning 3D Action Models from a few 2D videos for View Invariant Action Recognition
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
Pradeep Natarajan, Vivek Singh, Ram Nevatia
CVPR
2010
IEEE
14 years 2 months ago
Latent Hierarchical Structural Learning for Object Detection
We present a latent hierarchical structural learning method for object detection. An object is represented by a mixture of hierarchical tree models where the nodes represent objec...
Leo Zhu, Yuanhao Chen, Antonio Torralba, Alan Yuil...